ACL 2016 Papers

We present an approach to improve statistical machine translation of image descriptions by multimodal pivots defined in visual space. The key idea is to perform image retrieval over a database of images that are captioned in the target language, and use the captions of the most similar images for crosslingual reranking of translation outputs. Our approach does not depend on the availability of large amounts of in-domain parallel data, but only relies on available large datasets of monolingually captioned images, and on state-of-the-art convolutional neural networks to compute image similarities. Our experimental evaluation shows improvements of 1 BLEU point over strong baselines.

Detecting hypernymy relations is a key task in NLP, which is addressed in the literature using two complementary approaches. Distributional methods, whose supervised variants are the current best performers, and path-based methods, which received less research attention. We suggest an improved path-based algorithm, in which the dependency paths are encoded using a recurrent neural network, that achieves results comparable to distributional methods. We then extend the approach to integrate both path-based and distributional signals, significantly improving upon the state-of-the-art on this task.

Arbitrariness of the sign—the notion that the forms of words are unrelated to their meanings—is an underlying assumption of many linguistic theories. Two lines of research have recently challenged this assumption, but they produce differing characterizations of non-arbitrariness in language. Behavioral and corpus studies have confirmed the validity of localized form-meaning patterns manifested in limited subsets of the lexicon. Meanwhile, global (lexicon-wide) statistical analyses instead find diffuse form-meaning system-aticity across the lexicon as a whole. We bridge the gap with an approach that can detect both local and global form-meaning systematicity in language. In the kernel regression formulation we introduce, form-meaning relationships can be used to predict words’ distributional semantic vectors from their forms. Furthermore, we introduce a novel metric learning algorithm that can learn weighted edit distances that minimize kernel regression error. Our results suggest that the English lexicon exhibits far more global form-meaning systematicity than previously discovered, and that much of this systematicity is focused in localized form-meaning patterns.

We introduce a new language learning setting relevant to building adaptive natural language interfaces. It is inspired by Wittgenstein's language games: a human wishes to accomplish some task (e.g., achieving a certain configuration of blocks), but can only communicate with a computer, who performs the actual actions (e.g., removing all red blocks). The computer initially knows nothing about language and therefore must learn it from scratch through interaction, while the human adapts to the computer's capabilities. We created a game in a blocks world and collected interactions from 100 people playing it. First, we analyze the humans' strategies, showing that using compositionality and avoiding synonyms correlates positively with task performance. Second, we compare computer strategies, showing how to quickly learn a semantic parsing model from scratch, and that modeling pragmatics further accelerates learning for successful players.

Enabling a computer to understand a document so that it can answer comprehension questions is a central, yet unsolved goal of NLP. A key factor impeding its solution by machine learned systems is the limited availability of human-annotated data. Hermann et al. (2015) seek to solve this problem by creating over a million training examples by pairing CNN and Daily Mail news articles with their summarized bullet points, and show that a neural network can then be trained to give good performance on this task. In this paper, we conduct a thorough examination of this new reading comprehension task. Our primary aim is to understand what depth of language understanding is required to do well on this task. We approach this from one side by doing a careful hand-analysis of a small subset of the problems and from the other by showing that simple, carefully designed systems can obtain accuracies of 73.6% and 76.6% on these two datasets, exceeding current state-of-the-art results by 7-10% and approaching what we believe is the ceiling for performance on this task.

Part of the unique cultural heritage of China is the Chinese couplet. Given a sentence (namely an antecedent clause), people reply with another sentence (namely a subsequent clause) equal in length. Moreover, a special phenomenon is that corresponding characters from the same position in the two clauses match each other by following certain constraints on semantic and/or syntactic relatedness. Automatic couplet generation by computer is viewed as a difficult problem and has not been fully explored. In this paper, we formulate the task as a natural language generation problem using neural network structures. Given the issued antecedent clause, the system generates the subsequent clause via sequential language modeling. To satisfy special characteristics of couplets, we incorporate the attention mechanism and polishing schema into the encoding-decoding process. The couplet is generated incrementally and iteratively. A comprehensive evaluation, using perplexity and BLEU measurements as well as human judgments, has demonstrated the effectiveness of our proposed approach.

Semantic deficit is a symptom of language impairment in Alzheimer’s disease (AD). We present a generalizable method for automatic generation of information content units (ICUs) for a picture used in a standard clinical task, achieving high recall, 96.8%, of human-supplied ICUs. We use the automatically generated topic model to extract semantic features, and train a random forest classifier to achieve an F-score of 0.74 in binary classification of controls versus people with AD using a set of only 12 features. This is comparable to re-sults (0.72 F-score) with a set of 85 manual features. Adding semantic information to a set of standard lexicosyntactic and acoustic features improves F-score to 0.80. While control and dementia subjects discuss the same topics in the same contexts, controls are more informative per second of speech.

Existing knowledge-based question answering systems often rely on small annotated training data. While shallow methods like relation extraction are robust to data scarcity, they are less expressive than the deep meaning representation methods like semantic parsing, thereby failing at answering questions involving multiple constraints. Here we alleviate this problem by empowering a relation extraction method with additional evidence from Wikipedia. We first present a neural network based relation extractor to retrieve the candidate answers from Freebase, and then infer over Wikipedia to validate these answers. Experiments on the WebQuestions question answering dataset show that our method achieves an F_1 of 53.3%, a substantial improvement over the state-of-the-art.

Recently, knowledge graph embedding, which projects symbolic entities and relations into continuous vector space, has become a new, hot topic in artificial intelligence. This paper addresses a new issue of multiple relation semantics that a relation may have multiple meanings revealed by the entity pairs associated with the corresponding triples, and proposes a novel Gaussian mixture model for embedding, TransG. The new model can discover latent semantics for a relation and leverage a mixture of relation component vectors for embedding a fact triple. To the best of our knowledge, this is the first generative model for knowledge graph embedding, which is able to deal with multiple relation semantics. Extensive experiments show that the proposed model achieves substantial improvements against the state-of-the-art baselines.

In this paper, we propose a neural network model for graph-based dependency parsing which utilizes Bidirectional LSTM (BLSTM) to capture richer contextual information instead of using high-order factorization, and enable our model to use much fewer features than previous work. In addition, we propose an effective way to learn sentence segment embedding on sentence-level based on an extra forward LSTM network. Although our model uses only first-order factorization, experiments on English Peen Treebank and Chinese Penn Treebank show that our model could be competitive with previous higher-order graph-based dependency parsing models and state-of-the-art models.

Labeling topics learned by topic models is a challenging problem. Previous studies have used words, phrases and images to label topics. In this paper, we propose to use text summaries for topic labeling. Several sentences are extracted from the most related documents to form the summary for each topic. In order to obtain summaries with both high relevance, coverage and discrimination for all the topics, we propose an algorithm based on submodular optimization. Both automatic and manual analysis have been conducted on two real document collections, and we find 1) the summaries extracted by our proposed algorithm are superior over the summaries extracted by existing popular summarization methods; 2) the use of summaries as labels has obvious advantages over the use of words and phrases.

Anaphor resolution is an important task in NLP with many applications. Despite much research effort, it remains an open problem. The difficulty of the problem varies substantially across different sub-problems. One sub-problem, in particular, has been largely untouched by prior work despite occurring frequently throughout corpora: the anaphor that has multiple antecedents, which here we call multi-antecedent anaphors or manaphors. Current coreference resolvers restrict anaphors to at most a single antecedent. As we show in this paper, relaxing this constraint poses serious problems in coreference chain-building, where each chain is intended to refer to a single entity. This work provides a formalization of the new task with preliminary insights into multi-antecedent noun-phrase anaphors, and offers a method for resolving such cases that outperforms a number of baseline methods by a significant margin. Our system uses local agglomerative clustering on candidate antecedents and an existing coreference system to score clusters to determine which cluster of mentions is antecedent for a given anaphor. When we augment an existing coreference system with our proposed method, we observe a substantial increase in performance (0.6 absolute CoNLL F1) on an annotated

Learning distributed representations for relation instances is a central technique in downstream NLP applications. In order to address semantic modeling of relational patterns, this paper constructs a new dataset that provides multiple similarity ratings for every pair of relational patterns on the existing dataset. In addition, we conduct a comparative study of different encoders including additive composition, RNN, LSTM, and GRU for composing distributed representations of relational patterns. We also present Gated Additive Composition, which is an enhancement of additive composition with the gating mechanism. Experiments show that the new dataset does not only enable detailed analyses of the different encoders, but also provides a gauge to predict successes of distributed representations of relational patterns in the relation classification task.

We discuss an approximate similarity search for word embeddings, which is an operation to approximately find embeddings close to a given vector. We compared several metric-based search algorithms with hash-, tree, and graph-based indexing from different aspects. Our experimental results showed that a graph-based indexing exhibits robust performance and additionally provided useful information, e.g., vector normalization achieves an efficient search with cosine similarity.

Entity linking (EL) is the task of disambiguating mentions in text by associating them with entries in a predefined database of mentions (persons, organizations, etc). Most previous EL research has focused mainly on one language, English, with less attention being paid to other languages, such as Spanish or Chinese. In this paper, we introduce LIEL, a Language Independent Entity Linking system, which provides an EL framework which, once trained on one language, works remarkably well on a number of different languages without change. LIEL makes a joint global prediction over the entire document, employing a discriminative reranking framework with many domain and language-independent feature functions. Experiments on numerous benchmark datasets, show that the proposed system, once trained on one language, English, outperforms several state-of-the-art systems in English (by 4 points) and the trained model also works very well on Spanish (14 points better than a competitor system), demonstrating the viability of the approach.

In this paper, with the help of knowledge base, we build and formulate a semantic space to connect the source and target languages, and apply it to the sequence-to-sequence framework to pro-pose a Knowledge-Based Semantic Em-bedding (KBSE) method. In our KB-SE method, the source sentence is firstly mapped into a knowledge based semantic space, and the target sentence is generated using a recurrent neural network with the internal meaning preserved. Experiments are conducted on two translation tasks, the electric business data and movie data, and the results show that our proposed method can achieve outstanding performance, compared with both the traditional SMT methods and the existing encoder-decoder models.

The canonical word order of Japanese double object constructions has attracted considerable attention among linguists and has been a topic of many studies. However, most of these studies require either manual analyses or measurements of human characteristics such as brain activities or reading times for each example. Thus, while these analyses are reliable for the examples they focus on, they cannot be generalized to other examples. On the other hand, the trend of actual usage can be collected automatically from a large corpus. Thus, in this paper, we assume that there is a relationship between the canonical word order and the proportion of each word order in a large corpus and present a corpusbased analysis of canonical word order of Japanese double object constructions.

We present the first domain adaptation model for authorship attribution to leverage unlabeled data. The model includes extensions to structural correspondence learning needed to make it appropriate for the task. For example, we propose a median-based classification instead of the standard binary classification used in previous work. Our results show that punctuation-based character n -grams form excellent pivot features. We also show how singular value decomposition plays a critical role in achieving domain adaptation, and that replacing (instead of concatenating) non-pivot features with correspondence features yields better performance.

Hand-crafted features based on linguistic and domain-knowledge play crucial role in determining the performance of disease name recognition systems. Such methods are further limited by the scope of these features or in other words, their ability to cover the contexts or word dependencies within a sentence. In this work, we focus on reducing such dependencies and propose a domain-invariant framework for the disease name recognition task. In particular, we propose various end-to-end recurrent neural network (RNN) models for the tasks of disease name recognition and their classification into four pre-defined categories. We also utilize convolution neural network (CNN) in cascade of RNN to get character-based embedded features and employ it with word-embedded features in our model. We compare our models with the state-of-the-art results for the two tasks on NCBI disease dataset. Our results for the disease mention recognition task indicate that state-of-the-art performance can be obtained without relying on feature engineering. Further the proposed models obtained improved performance on the classification task of disease names.