COLING 2024 论文列表

Empathetic response generation aims to understand the user’s feelings emotionally and generate responses with appropriate emotion. According to psychological theories, empathy consists of two main aspects: affection and cognition. However, existing works lack the perception of fine-grained dialogue emotion propagation, as well as have limitations in reasoning about the intentions of users on cognition, which affect the quality of empathetic response. To this end, we propose to generate Empathetic response based on in-context Commonsense reasoning and Reinforcement Learning (EmpCRL). First, we use a current popular large language model combined with multi-view contextual reasoning to broaden the cognitive boundaries through in-context learning. Furthermore, we infer the response emotion by jointly modeling the dialogue history and emotion flow, and achieve the control of response emotion and diversity through reinforcement learning. Extensive experiments on EmpatheticDialogues dataset show that our model outperforms state-of-the-art models in both automatic and human evaluation.

Emotion recognition in conversation (ERC) is a field that aims to classify the emotion of each utterance within conversational contexts. This presents significant challenges, particularly in handling emotional ambiguity across various speakers and contextual factors. Existing ERC approaches have primarily focused on modeling conversational contexts while incorporating only superficial speaker attributes such as names, memories, and interactions. Recent works introduce personality as an essential deep speaker factor for emotion recognition, but relies on static personality, overlooking dynamic variability during conversations. Advances in personality psychology conceptualize personality as dynamic, proposing that personality states can change across situations. In this paper, we introduce ERC-DP, a novel model considering the dynamic personality of speakers during conversations. ERC-DP accounts for past utterances from the same speaker as situation impacting dynamic personality. It combines personality modeling with prompt design and fine-grained classification modules. Through a series of comprehensive experiments, ERC-DP demonstrates superior performance on three benchmark conversational datasets.

Emotions are a central aspect of communication. Consequently, emotion analysis (EA) is a rapidly growing field in natural language processing (NLP). However, there is no consensus on scope, direction, or methods. In this paper, we conduct a thorough review of 154 relevant NLP publications from the last decade. Based on this review, we address four different questions: (1) How are EA tasks defined in NLP? (2) What are the most prominent emotion frameworks and which emotions are modeled? (3) Is the subjectivity of emotions considered in terms of demographics and cultural factors? and (4) What are the primary NLP applications for EA? We take stock of trends in EA and tasks, emotion frameworks used, existing datasets, methods, and applications. We then discuss four lacunae: (1) the absence of demographic and cultural aspects does not account for the variation in how emotions are perceived, but instead assumes they are universally experienced in the same manner; (2) the poor fit of emotion categories from the two main emotion theories to the task; (3) the lack of standardized EA terminology hinders gap identification, comparison, and future goals; and (4) the absence of interdisciplinary research isolates EA from insights in other fields. Our work will enable more focused research into EA and a more holistic approach to modeling emotions in NLP.

We developped a web app for ascribing verbal descriptions to expressive audiovisual utterances. These descriptions are limited to lists of adjectives that are either suggested via a navigation in emotional latent spaces built using discriminant analysis of BERT embeddings or entered freely by subjects. We show that such verbal descriptions collected on-line via Prolific on massive data (310 participants, 12620 labelled utterances up-to-now) provide Expressive Multimodal Text-to-Speech Synthesis with precise verbal control over desired emotional content

In an emotional conversation, emotions are causally transmitted among communication participants, constituting a fundamental conversational feature that can facilitate the comprehension of intricate changes in emotional states during the conversation and contribute to neutralizing emotional semantic bias in utterance caused by the absence of modality information. Therefore, emotional transition (ET) plays a crucial role in the task of Emotion Recognition in Conversation (ERC) that has not received sufficient attention in current research. In light of this, an Emotional Transition-based Emotion Recognizer (EmoTrans) is proposed in this paper. Specifically, we concatenate the most recent utterances with their corresponding speakers to construct the model input, known as samples, each with several placeholders to implicitly express the emotions of contextual utterances. Based on these placeholders, two components are developed to make the model sensitive to emotions and effectively capture the ET features in the sample. Furthermore, an ET-based Contrastive Learning (CL) is developed to compact the representation space, making the model achieve more robust sample representations. We conducted exhaustive experiments on four widely used datasets and obtained competitive experimental results, especially, new state-of-the-art results obtained on MELD and IEMOCAP, demonstrating the superiority of EmoTrans.

Emotion-cause pair extraction (ECPE) main focus is on extracting all potential emotion clauses and corresponding cause clauses from unannotated documents. Existing methods achieve promising results with the help of fine-tuning and prompt paradigms, but they present three downsides. First, most approaches cannot distinguish between the emotion-cause pairs that belong to different types of emotions, limiting the existing approaches’ applicability. Second, existing prompt methods utilize a one-to-one mapping relation to achieve label words to category mapping, which brings considerable bias to the results. Third, existing methods achieve the cause extraction task supported by explicit semantic understanding or basic prompt templates, ignoring the implicit information contained in the cause clauses themselves. To solve these issues, we propose an Emotion knowledge-aware Prompt-tuning for Emotion-Cause Pair Extraction (EmoPrompt-ECPE) method, which integrate the knowledge of emotion categories in the ECPE task and mine the implicit knowledge of cause clauses. Specifically, we inject the latent knowledge of the cause clauses and the emotion types into the prompt template. Besides, we extend the emotion labels for many-to-one mapping of label words to categories with an external emotion word base. Furthermore, we utilize the cosine similarity filtering of the label word base to reduce the noise caused by knowledge introduction. Experiments on both Chinese and English benchmark datasets show that our approach can achieve state-of-the-art results. Our code and data can be found at: https://github.com/xy-xiaotudou/EmoPrompt-ECPE.

Emotion analysis often involves the categorization of isolated textual units, but these are parts of longer discourses, like dialogues or stories. This leads to two different established emotion classification setups: (1) Classification of a longer text into one or multiple emotion categories. (2) Classification of the parts of a longer text (sentences or utterances), either (2a) with or (2b) without consideration of the context. None of these settings, does, however, enable to answer the question which emotion is presumably experienced at a specific moment in time. For instance, a customer’s request of “My computer broke.” would be annotated with anger. This emotion persists in a potential follow-up reply “It is out of warranty.” which would also correspond to the global emotion label. An alternative reply “We will send you a new one.” might, in contrast, lead to relief. Modeling these label relations requires classification of textual parts under consideration of the past, but without access to the future. Consequently, we propose a novel annotation setup for emotion categorization corpora, in which the annotations reflect the emotion up to the annotated sentence. We ensure this by uncovering the textual parts step-by-step to the annotator, asking for a label in each step. This perspective is important to understand the final, global emotion, while having access to the individual sentence’s emotion contributions to this final emotion. In modeling experiments, we use these data to check if the context is indeed required to automatically predict such cumulative emotion progressions.

Event Extraction (EE) is a challenging task that aims to extract structural event-related information from unstructured text. Traditional methods for EE depend on manual annotations, which are both expensive and scarce. Furthermore, the existing datasets mostly follow the long-tail distribution, severely hindering the previous methods of modeling tail types. Two techniques can address this issue: transfer learning and data generation. However, the existing methods based on transfer learning still rely on pre-training with a large amount of labeled data in the source domain. Additionally, the quality of data generated by previous data generation methods is difficult to control. In this paper, leveraging Large Language Models (LLMs), we propose novel methods for event extraction and generation based on dialogues, overcoming the problems of relying on source domain data and maintaining data quality. Specifically, this paper innovatively transforms the EE task into multi-turn dialogues, guiding LLMs to learn event schemas from historical dialogue information and output structural events. Furthermore, we introduce a novel LLM-based method for generating high-quality data, significantly improving traditional models’ performance with various paradigms and structures, especially on tail types. Adequate experiments on real-world datasets demonstrate the effectiveness of the proposed event extraction and data generation methods.

Behavioral coding (BC) in motivational interviewing (MI) holds great potential for enhancing the efficacy of MI counseling. However, manual coding is labor-intensive, and automation efforts are hindered by the lack of data due to the privacy of psychotherapy. To address these challenges, we introduce BiMISC, a bilingual dataset of MI conversations in English and Dutch, sourced from real counseling sessions. Expert annotations in BiMISC adhere strictly to the motivational interviewing skills code (MISC) scheme, offering a pivotal resource for MI research. Additionally, we present a novel approach to elicit the MISC expertise from Large language models (LLMs) for MI coding. Through the in-depth analysis of BiMISC and the evaluation of our proposed approach, we demonstrate that the LLM-based approach yields results closely aligned with expert annotations and maintains consistent performance across different languages. Our contributions not only furnish the MI community with a valuable bilingual dataset but also spotlight the potential of LLMs in MI coding, laying the foundation for future MI research.

The efficacy of neural “retrieve and generate” systems is well established for question answering (QA) over unstructured text. Recent efforts seek to extend this approach to knowledge graph (KG) QA by converting structured triples to unstructured text. However, the relevance of KG triples retrieved by these systems limits their accuracy. In this paper, we improve the relevance of retrieved triples using a carefully designed re-ranker. Specifically, our pipeline (i) retrieves over documents of triples grouped by entity, (ii) re-ranks triples from these documents with context: triples in the 1-hop neighborhood of the documents’ subject entity, and (iii) generates an answer from highly relevant re-ranked triples. To train our re-ranker, we propose a novel “triple-level” labeling strategy that infers fine-grained labels and shows that these significantly improve the relevance of retrieved information. We show that the resulting “retrieve, re-rank, and generate” pipeline significantly improves upon prior KGQA systems, achieving a new state-of-the-art on FreebaseQA by 5.56% Exact Match. We perform multiple ablations that reveal the distinct benefits of our contextual re-ranker and labeling strategy and conclude with a case study that highlights opportunities for future works.

Sequence-to-sequence models have become the de facto standard for Abstract Meaning Representation (AMR) parsing due to their high-quality performance. However, these systems face efficiency challenges because of their large model size and computational time, which limit their accessibility within the research community. This paper aims to break down these barriers by introducing a novel linearization and system that significantly enhances the efficiency and accessibility of previous AMR parsers. First, we propose our novel Compact linearization that simplifies encoding, thereby reducing the number of tokens by between 40% and 50%. Second, we present CLAP, an innovative modular system that maintains the model’s high performance while achieving remarkable 80% reduction in training and inference times. Furthermore, CLAP is compatible with multiple autoregressive Language Models (LM) and tokenizers, such as BART, T5, and others. These advancements underscore the importance of optimizing sequence-to-sequence models in AMR parsing, thus democratizing access to high-quality semantic analysis. Our code is publicly available at https://github.com/SapienzaNLP/clap/.

We investigate the roles that efficiency and effectiveness play in speakers’ repetition of shared word sequences, or constructions, in task-oriented dialogue. We find that repeating constructions has negative effects on information rate and positive effects on rate of delivery, that information rate managing strategies are predictive of task success, and that this varies by the communicative function of the constructions being repeated. More effective dialogue is characterised by greater levels of shared construction usage and more efficient task-related repetition; while task-agnostic repetition can seem redundant, it can serve important efficiency and effectiveness functions. Our results provide a nuanced picture of the importance of repetition and of developing a shared lexicon for both efficiency and effectiveness in task-oriented dialogue.

Diffusion models have become a powerful generative modeling paradigm, achieving great success in continuous data patterns. However, the discrete nature of text data results in compatibility issues between continuous diffusion models (CDMs) and pre-trained language models (PLMs). That is, the performance of diffusion models even degrades when combined with PLMs. To alleviate this issue, we propose to utilize a pre-trained decoder to convert the denoised embedding vectors into natural language instead of using the widely used rounding operation. In this way, CDMs can be more effectively combined with PLMs. Additionally, considering that existing noise schedules in text diffusion models do not take into account the linguistic differences among tokens, which violates the easy-first policy for text generation, we propose a linguistic easy-first schedule that incorporates the measure of word importance, conforming to easy-first-generation linguistic features and bringing about improved generation quality. Experiment results on the E2E dataset and five controllable tasks show that our approach can combine the merits of CDMs and PLMs, significantly outperforming other diffusion-based models.

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, their enormous parameter size and extremely high requirements for compute power pose challenges for their practical deployment. Recent research has revealed that specific capabilities of LLMs, such as numerical reasoning, can be transferred to smaller models through distillation. Some studies explore the potential of leveraging LLMs to perform table-based reasoning. However, there has been no prior work focusing on table reasoning skills in smaller models specifically tailored for scientific table-to-text generation tasks. In this paper, we propose a novel table-based reasoning distillation approach, with the aim of distilling LLMs into tailored smaller models. Our experimental results have shown that a 220 million parameter model (Flan-T5-base) fine-tuned using distilled data, not only achieves a significant improvement compared to traditionally fine-tuned baselines, but also surpasses specific LLMs on a scientific table-to-text generation dataset. Our code is available at https://github.com/Bernard-Yang/DistillTableCoT.

We introduce Eesthetic, a comprehensive Estonian noun and verb lexicon sourced from the Ekilex database. It documents 5475 nouns inflecting for 28 paradigm cells and 5076 verbs inflecting for 51 cells, and comprises a total of 452885 inflected forms. Our openly accessible machine-readable dataset adheres to the Paralex standard. It comprises CSV tables linked by formal relationships. Metadata in JSON format, following the Frictionless standard, provides detailed descriptions of the tables and dataset. The lexicon offers extensive linguistic annotations, including orthographic forms, automatically transcribed phonemic transcriptions, non-canonical morphological phenomena such as overabundance and defectiveness, rich mapping of the paradigm cells and feature-values to other notation schemes, a decomposition of phonemes in distinctive features, and annotation of inflection classes. It is suited for both monolingual and comparative research, enabling qualitative and quantitative analysis. This paper outlines the creation process, rationale, and resulting structure, along with our set of rules for automatic orthography-to-phonemic transcription conversion.

This paper describes a corpus consisting of real-world dialogues in English between users and a task-oriented conversational agent, with interactions revolving around the description of finite state automata. The creation of this corpus is part of a larger research project aimed at developing tools for an easier access to educational content, especially in STEM fields, for users with visual impairments. The development of this corpus was precisely motivated by the aim of providing a useful resource to support the design of such tools. The core feature of this corpus is that its creation involved both sighted and visually impaired participants, thus allowing for a greater diversity of perspectives and giving the opportunity to identify possible differences in the way the two groups of participants interacted with the agent. The paper introduces this corpus, giving an account of the process that led to its creation, i.e. the methodology followed to obtain the data, the annotation scheme adopted, and the analysis of the results. Finally, the paper reports the results of a classification experiment on the annotated corpus, and an additional experiment to assess the annotation capabilities of three large language models, in view of a further expansion of the corpus.

Anthropogenic ecological crisis constitutes a significant challenge that all within the academy must urgently face, including the Natural Language Processing (NLP) community. While recent years have seen increasing work revolving around climate-centric discourse, crucial environmental and ecological topics outside of climate change remain largely unaddressed, despite their prominent importance. Mainstream NLP tasks, such as sentiment analysis, dominate the scene, but there remains an untouched space in the literature involving the analysis of environmental impacts of certain events and practices. To address this gap, this paper presents EcoVerse, an annotated English Twitter dataset of 3,023 tweets spanning a wide spectrum of environmental topics. We propose a three-level annotation scheme designed for Eco-Relevance Classification, Stance Detection, and introducing an original approach for Environmental Impact Analysis. We detail the data collection, filtering, and labeling process that led to the creation of the dataset. Remarkable Inter-Annotator Agreement indicates that the annotation scheme produces consistent annotations of high quality. Subsequent classification experiments using BERT-based models, including ClimateBERT, are presented. These yield encouraging results, while also indicating room for a model specifically tailored for environmental texts. The dataset is made freely available to stimulate further research.

Research probing the language comprehension of visio-linguistic models has gained traction due to their remarkable performance on various tasks. We introduce EViL-Probe, a composite benchmark that processes existing probing datasets into a unified format and reorganizes them based on the linguistic categories they probe. On top of the commonly used negative probes, this benchmark introduces positive probes to more rigorously test the robustness of models. Since the language side alone may introduce a bias models could exploit in solving the probes, we estimate the difficulty of the individual subsets with a language-only baseline. Using the benchmark to probe a set of state-of-the-art visio-linguistic models sheds light on how sensitive they are to the different linguistic categories. Results show that the benchmark is challenging for all models we probe, as their performance is around the chance baseline for many of the categories. The only category all models are able to handle relatively well are nouns. Additionally, models that use a Vision Transformer to process the images are also somewhat robust against probes targeting color and image type. Among these models, our enrichment of EViL-Probe with positive probes helps further discriminate performance, showing BLIP to be the overall best-performing model.

Depression impacts millions worldwide, with increasing efforts to use social media data for early detection and intervention. Traditional Risk Detection (TRD) uses a user’s complete posting history for predictions, while Early Risk Detection (ERD) seeks early detection in a user’s posting history, emphasizing the importance of prediction earliness. However, ERD remains relatively underexplored due to challenges in balancing accuracy and earliness, especially with evolving partial data. To address this, we introduce the Early Sensing Depression Model (ESDM), which comprises two modules classification with partial information module (CPI) and decision for classification moment module (DMC), alongside an early detection loss function. Experiments show ESDM outperforms benchmarks in both earliness and accuracy.