COLING 2020 论文列表

A prominent problem faced by conversational agents working with large documents (Eg: email-based assistants) is the frequent presence of information in the document that is irrelevant to the assistant. This in turn makes it harder for the agent to accurately detect intents, extract entities relevant to those intents and perform the desired action. To address this issue we present a neural model for scoping relevant information for the agent from a large document. We show that when used as the first step in a popularly used email-based assistant for helping users schedule meetings, our proposed model helps improve the performance of the intent detection and entity extraction tasks required by the agent for correctly scheduling meetings: across a suite of 6 downstream tasks, by using our proposed method, we observe an average gain of 35% in precision without any drop in recall. Additionally, we demonstrate that the same approach can be used for component level analysis in large documents, such as signature block identification.

Scientific keyphrase identification and classification is the task of detecting and classifying keyphrases from scholarly text with their types from a set of predefined classes. This task has a wide range of benefits, but it is still challenging in performance due to the lack of large amounts of labeled data required for training deep neural models. In order to overcome this challenge, we explore pre-trained language models BERT and SciBERT with intermediate task transfer learning, using 42 data-rich related intermediate-target task combinations. We reveal that intermediate task transfer learning on SciBERT induces a better starting point for target task fine-tuning compared with BERT and achieves competitive performance in scientific keyphrase identification and classification compared to both previous works and strong baselines. Interestingly, we observe that BERT with intermediate task transfer learning fails to improve the performance of scientific keyphrase identification and classification potentially due to significant catastrophic forgetting. This result highlights that scientific knowledge achieved during the pre-training of language models on large scientific collections plays an important role in the target tasks. We also observe that sequence tagging related intermediate tasks, especially syntactic structure learning tasks such as POS Tagging, tend to work best for scientific keyphrase identification and classification.

Natural Language Query interfaces allow the end-users to access the desired information without the need to know any specialized query language, data storage, or schema details. Even with the recent advances in NLP research space, the state-of-the-art QA systems fall short of understanding implicit intents of real-world Business Intelligence (BI) queries in enterprise systems, since Natural Language Understanding still remains an AI-hard problem. We posit that deploying ontology reasoning over domain semantics can help in achieving better natural language understanding for QA systems. In this paper, we specifically focus on building a Schema Aware Semantic Reasoning Framework that translates natural language interpretation as a sequence of solvable tasks by an ontology reasoner. We apply our framework on top of an ontology based, state-of-the-art natural language question-answering system ATHENA, and experiment with 4 benchmarks focused on BI queries. Our experimental numbers empirically show that the Schema Aware Semantic Reasoning indeed helps in achieving significantly better results for handling BI queries with an average accuracy improvement of ~30%

This paper introduces a method that efficiently reduces the computational cost and parameter size of Transformer. The proposed model, refer to as Group-Transformer, splits feature space into multiple groups, factorizes the calculation paths, and reduces computations for the group interaction. Extensive experiments on two benchmark tasks, enwik8 and text8, prove our model’s effectiveness and efficiency in small-scale Transformers. To the best of our knowledge, Group-Transformer is the first attempt to design Transformer with the group strategy, widely used for efficient CNN architectures.

We present scalable Universal Dependency (UD) treebank synthesis techniques that exploit advances in language representation modeling which leverage vast amounts of unlabeled general-purpose multilingual text. We introduce a data augmentation technique that uses synthetic treebanks to improve production-grade parsers. The synthetic treebanks are generated using a state-of-the-art biaffine parser adapted with pretrained Transformer models, such as Multilingual BERT (M-BERT). The new parser improves LAS by up to two points on seven languages. The production models’ LAS performance improves as the augmented treebanks scale in size, surpassing performance of production models trained on originally annotated UD treebanks.

Keyphrases in a research paper succinctly capture the primary content of the paper and also assist in indexing the paper at a concept level. Given the huge rate at which scientific papers are published today, it is important to have effective ways of automatically extracting keyphrases from a research paper. In this paper, we present a novel method, Syntax and Semantics Aware Keyphrase Extraction (SaSAKE), to extract keyphrases from research papers. It uses a transformer architecture, stacking up sentence encoders to incorporate sequential information, and graph encoders to incorporate syntactic and semantic dependency graph information. Incorporation of these dependency graphs helps to alleviate long-range dependency problems and identify the boundaries of multi-word keyphrases effectively. Experimental results on three benchmark datasets show that our proposed method SaSAKE achieves state-of-the-art performance in keyphrase extraction from scientific papers.

Multimodal sentiment analysis aims to predict sentiment of language text with the help of other modalities, such as vision and acoustic features. Previous studies focused on learning the joint representation of multiple modalities, ignoring some useful knowledge contained in language modal. In this paper, we try to incorporate sentimental words knowledge into the fusion network to guide the learning of joint representation of multimodal features. Our method consists of two components: shallow fusion part and aggregation part. For the shallow fusion part, we use crossmodal coattention mechanism to obtain bidirectional context information of each two modals to get the fused shallow representations. For the aggregation part, we design a multitask of sentimental words classification to help and guide the deep fusion of the three modalities and obtain the final sentimental words aware fusion representation. We carry out several experiments on CMU-MOSI, CMU-MOSEI and YouTube datasets. The experimental results show that introducing sentimental words prediction as a multitask can really improve the fusion representation of multiple modalities.

Text-to-SQL systems offers natural language interfaces to databases, which can automatically generates SQL queries given natural language questions. On the WikiSQL benchmark, state-of- the-art text-to-SQL systems typically take a slot-filling approach by building several specialized models for each type of slot. Despite being effective, such modularized systems are complex and also fall short in jointly learning for different slots. To solve these problems, this paper proposes a novel approach that formulates the task as a question answering problem, where different slots are predicted by a unified machine reading comprehension (MRC) model. For this purpose, we use a BERT-based MRC model, which can also benefit from intermediate training on other MRC datasets. The proposed method can achieve competitive results on WikiSQL, suggesting it being a promising direction for text-to-SQL.

We propose a reference-less metric trained on manual evaluations of system outputs for grammatical error correction (GEC). Previous studies have shown that reference-less metrics are promising; however, existing metrics are not optimized for manual evaluations of the system outputs because no dataset of the system output exists with manual evaluation. This study manually evaluates outputs of GEC systems to optimize the metrics. Experimental results show that the proposed metric improves correlation with the manual evaluation in both system- and sentence-level meta-evaluation. Our dataset and metric will be made publicly available.

Contextualised embeddings such as BERT have become de facto state-of-the-art references in many NLP applications, thanks to their impressive performances. However, their opaqueness makes it hard to interpret their behaviour. SLICE is a hybrid model that combines supersense labels with contextual embeddings. We introduce a weakly supervised method to learn interpretable embeddings from raw corpora and small lists of seed words. Our model is able to represent both a word and its context as embeddings into the same compact space, whose dimensions correspond to interpretable supersenses. We assess the model in a task of supersense tagging for French nouns. The little amount of supervision required makes it particularly well suited for low-resourced scenarios. Thanks to its interpretability, we perform linguistic analyses about the predicted supersenses in terms of input word and context representations.

We present RuSemShift, a large-scale manually annotated test set for the task of semantic change modeling in Russian for two long-term time period pairs: from the pre-Soviet through the Soviet times and from the Soviet through the post-Soviet times. Target words were annotated by multiple crowd-source workers. The annotation process was organized following the DURel framework and was based on sentence contexts extracted from the Russian National Corpus. Additionally, we report the performance of several distributional approaches on RuSemShift, achieving promising results, which at the same time leave room for other researchers to improve.

Unsupervised neural machine translation (UNMT) has recently attracted great interest in the machine translation community. The main advantage of the UNMT lies in its easy collection of required large training text sentences while with only a slightly worse performance than supervised neural machine translation which requires expensive annotated translation pairs on some translation tasks. In most studies, the UMNT is trained with clean data without considering its robustness to the noisy data. However, in real-world scenarios, there usually exists noise in the collected input sentences which degrades the performance of the translation system since the UNMT is sensitive to the small perturbations of the input sentences. In this paper, we first time explicitly take the noisy data into consideration to improve the robustness of the UNMT based systems. First of all, we clearly defined two types of noises in training sentences, i.e., word noise and word order noise, and empirically investigate its effect in the UNMT, then we propose adversarial training methods with denoising process in the UNMT. Experimental results on several language pairs show that our proposed methods substantially improved the robustness of the conventional UNMT systems in noisy scenarios.

Neural models have achieved great success on the task of machine reading comprehension (MRC), which are typically trained on hard labels. We argue that hard labels limit the model capability on generalization due to the label sparseness problem. In this paper, we propose a robust training method for MRC models to address this problem. Our method consists of three strategies, 1) label smoothing, 2) word overlapping, 3) distribution prediction. All of them help to train models on soft labels. We validate our approach on the representative architecture - ALBERT. Experimental results show that our method can greatly boost the baseline with 1% improvement in average, and achieve state-of-the-art performance on NewsQA and QUOREF.

Deep pre-trained language models tend to become ubiquitous in the field of Natural Language Processing (NLP). These models learn contextualized representations by using a huge amount of unlabeled text data and obtain state of the art results on a multitude of NLP tasks, by enabling efficient transfer learning. For other languages besides English, there are limited options of such models, most of which are trained only on multi-lingual corpora. In this paper we introduce a Romanian-only pre-trained BERT model – RoBERT – and compare it with different multi-lingual models on seven Romanian specific NLP tasks grouped into three categories, namely: sentiment analysis, dialect and cross-dialect topic identification, and diacritics restoration. Our model surpasses the multi-lingual models, as well as a another mono-lingual implementation of BERT, on all tasks.

Though preceding work in computational argument quality (AQ) mostly focuses on assessing overall AQ, researchers agree that writers would benefit from feedback targeting individual dimensions of argumentation theory. However, a large-scale theory-based corpus and corresponding computational models are missing. We fill this gap by conducting an extensive analysis covering three diverse domains of online argumentative writing and presenting GAQCorpus: the first large-scale English multi-domain (community Q&A forums, debate forums, review forums) corpus annotated with theory-based AQ scores. We then propose the first computational approaches to theory-based assessment, which can serve as strong baselines for future work. We demonstrate the feasibility of large-scale AQ annotation, show that exploiting relations between dimensions yields performance improvements, and explore the synergies between theory-based prediction and practical AQ assessment.

Indigenous languages have been very challenging when dealing with NLP tasks and applications because of multiple reasons. These languages, in linguistic typology, are polysynthetic and highly inflected with rich morphophonemics and variable dialectal-dependent spellings; which affected studies on any NLP task in the recent years. Moreover, Indigenous languages have been considered as low-resource and/or endangered; which poses a great challenge for research related to Artificial Intelligence and its fields, such as NLP and machine learning. In this paper, we propose a study on the Inuktitut language through pre-processing and neural machine translation, in order to revitalize the language which belongs to the Inuit family, a type of polysynthetic languages spoken in Northern Canada. Our focus is concentrated on: (1) the preprocessing phase, and (2) applications on specific NLP tasks such as morphological analysis and neural machine translation, both for Indigenous languages of Canada. Our evaluations in the context of lowresource Inuktitut-English Neural Machine Translation, showed significant improvements of the proposed approach compared to the state-of-the-art.

We introduce a deep learning model to learn the set of enumerated job skills associated with a job description. In our analysis of a large-scale government job portal mycareersfuture.sg, we observe that as much as 65% of job descriptions miss describing a significant number of relevant skills. Our model addresses this task from the perspective of an extreme multi-label classification (XMLC) problem, where descriptions are the evidence for the binary relevance of thousands of individual skills. Building upon the current state-of-the-art language modeling approaches such as BERT, we show our XMLC method improves on an existing baseline solution by over 9% and 7% absolute improvements in terms of recall and normalized discounted cumulative gain. We further show that our approach effectively addresses the missing skills problem, and helps in recovering relevant skills that were missed out in the job postings by taking into account the structured semantic representation of skills and their co-occurrences through a Correlation Aware Bootstrapping process. We further show that our approach, to ensure the BERT-XMLC model accounts for structured semantic representation of skills and their co-occurrences through a Correlation Aware Bootstrapping process, effectively addresses the missing skills problem, and helps in recovering relevant skills that were missed out in the job postings. To facilitate future research and replication of our work, we have made the dataset and the implementation of our model publicly available.

In this paper, we study review generation given a set of attribute identifiers which are user ID, product ID and rating. This is a difficult subtask of natural language generation since models are limited to the given identifiers, without any specific descriptive information regarding the inputs, when generating the text. The capacity of these models is thus confined and dependent to how well the models can capture vector representations of attributes. We thus propose to additionally leverage references, which are selected from a large pool of texts labeled with one of the attributes, as textual information that enriches inductive biases of given attributes. With these references, we can now pose the problem as an instance of text-to-text generation, which makes the task easier since texts that are syntactically, semantically similar with the output text are provided as input. Using this framework, we address issues such as selecting references from a large candidate set without textual context and improving the model complexity for generation. Our experiments show that our models improve over previous approaches on both automatic and human evaluation metrics.

Transformer becomes the state-of-the-art translation model, while it is not well studied how each intermediate component contributes to the model performance, which poses significant challenges for designing optimal architectures. In this work, we bridge this gap by evaluating the impact of individual component (sub-layer) in trained Transformer models from different perspectives. Experimental results across language pairs, training strategies, and model capacities show that certain components are consistently more important than the others. We also report a number of interesting findings that might help humans better analyze, understand and improve Transformer models. Based on these observations, we further propose a new training strategy that can improves translation performance by distinguishing the unimportant components in training.