Benchmarks

The paper considers how to scale up dialogue protocols to multilogue, settings with multiple conversationalists. We extract two benchmarks to evaluate scaled up protocols based on the long distance resolution …...

News reports, social media streams, blogs, digitized archives and books are part of a plethora of reading sources that people face every day. This raises the question of how to …...

We present a fast, simple, and high-accuracy short answer grading system. Given a short- answer question and its correct answer, key measures of the correctness of a student re- sponse …...

Many language generation tasks require the production of text conditioned on both structured and unstructured inputs. We present a novel neural network architec- ture which generates an output sequence conditioned …...

Training neural network language mod- els over large vocabularies is computa- tionally costly compared to count-based models such as Kneser-Ney. We present a systematic comparison of neural strate- gies to …...

AbstractNeural word segmentation research has benefited from large-scale raw texts by leveraging them for pretraining character and word embeddings. On the other hand, statistical segmentation research has exploited richer sources …...

Supervised models for Word Sense Disambiguation (WSD) currently yield to state-of-the-art results in the most popular benchmarks. Despite the recent...

AbstractA large body of research into semantic textual similarity has focused on constructing state-of-the-art embeddings using sophisticated modelling, careful choice of learning signals and many clever tricks. By contrast, little …...

AbstractWe consider the task of inferring “is-a” relationships from large text corpora. For this purpose, we propose a new method combining hyperbolic embeddings and Hearst patterns. This approach allows us …...

AbstractWe propose a new type of representation learning method that models words, phrases and sentences seamlessly. Our method does not depend on word segmentation and any human-annotated resources (e.g., word …...

AbstractLexical relations describe how meanings of terms relate to each other. Typical examples include hypernymy, synonymy, meronymy, etc. Automatic distinction of lexical relations is vital for NLP applications, and also …...

AbstractThis paper studies the task of Relation Extraction (RE) that aims to identify the semantic relations between two entity mentions in text. In the deep learning models for RE, it …...

AbstractKnowledge Graphs (KG) are multi-relational graphs consisting of entities as nodes and relations among them as typed edges. Goal of the Question Answering over KG (KGQA) task is to answer …...

AbstractAspect-level sentiment analysis aims to recognize the sentiment polarity of an aspect or a target in a comment. Recently, graph convolutional networks based on linguistic dependency trees have been studied …...

AbstractPretrained Language Models (PLMs) have improved the performance of natural language understanding in recent years. Such models are pretrained on large corpora, which encode the general prior knowledge of natural …...

AbstractFollowing decades of massive digitization, an unprecedented amount of historical document facsimiles can now be retrieved and accessed via cultural heritage online portals. If this represents a huge step forward …...

AbstractText generation often requires high-precision output that obeys task-specific rules. This fine-grained control is difficult to enforce with off-the-shelf deep learning models. In this work, we consider augmenting neural generation …...

AbstractThe embedding layers transforming input words into real vectors are the key components of deep neural networks used in natural language processing. However, when the vocabulary is large, the corresponding …...

AbstractThe training process of scientific NER models is commonly performed in two steps: i) Pre-training a language model by self-supervised tasks on huge data and ii) fine-tune training with small …...

AbstractZero-shot learning has been a tough problem since no labeled data is available for unseen classes during training, especially for classes with low similarity. In this situation, transferring from seen …...

AbstractZero pronoun recovery and resolution aim at recovering the dropped pronoun and pointing out its anaphoric mentions, respectively. We propose to better explore their interaction by solving both tasks together, …...

AbstractNeural conversation models have shown great potentials towards generating fluent and informative responses by introducing external background knowledge. Nevertheless, it is laborious to construct such knowledge-grounded dialogues, and existing models …...

AbstractEffective representation of biomedical names for downstream NLP tasks requires the encoding of both lexical as well as domain-specific semantic information. Ideally, the synonymy and semantic relatedness of names should …...

AbstractWe study controllable text summarization, which allows users to gain control on a particular attribute (e.g., length limit) of the generated summaries. In this work, we propose a novel training …...

AbstractIn this work, we investigate the problems of semantic parsing in a few-shot learning setting. In this setting, we are provided with k utterance-logical form pairs per new predicate. The …...

Neural sequence models exhibit limited com- positional generalization ability in semantic parsing tasks. Compositional generalization requires algebraic recombination, i.e., dynam- ically recombining structured expressions in a recursive manner. However, most …...

AbstractScheduled sampling is widely used to mitigate the exposure bias problem for neural machine translation. Its core motivation is to simulate the inference scene during training by replacing ground-truth tokens …...

AbstractCommonsense is a quintessential human capacity that has been a core challenge to Artificial Intelligence since its inception. Impressive results in Natural Language Processing tasks, including in commonsense reasoning, have …...

AbstractNeural information retrieval (IR) has greatly advanced search and other knowledge-intensive language tasks. While many neural IR methods encode queries and documents into single-vector representations, late interaction models produce multi-vector …...

AbstractRecently, Bert-based models have dominated the research of Chinese spelling correction (CSC). These methods have two limitations: (1) they have poor performance on multi-typo texts. In such texts, the context …...

AbstractText semantic matching is a fundamental task that has been widely used in various scenarios, such as community question answering, information retrieval, and recommendation. Most state-of-the-art matching models, e.g., BERT, …...

AbstractDespite recent improvements in abstractive summarization, most current approaches generate summaries that are not factually consistent with the source document, severely restricting their trust and usage in real-world applications. Recent …...

AbstractWelsh is an official language in Wales and is spoken by an estimated 884,300 people (29.2% of the population of Wales). Despite this status and estimated increase in speaker numbers …...

AbstractParaphrase generation is a longstanding NLP task and achieves great success with the aid of large corpora. However, transferring a paraphrasing model to another domain encounters the problem of domain …...

AbstractGrounding dialogue generation by extra knowledge has shown great potentials towards building a system capable of replying with knowledgeable and engaging responses. Existing studies focus on how to synthesize a …...

AbstractAspect-based sentiment analysis (ABSA) has received increasing attention recently. ABSA can be divided into multiple tasks according to the different extracted elements. Existing generative methods usually treat the output as …...

AbstractWe introduce Textstar, a graph-based summarization and keyphrase extraction system that builds a document graph using only lemmatization and POS tagging. The document graph aggregates connections between lemma and sentence …...

AbstractEstablishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention. Recent common practice is to construct a two-stage pipeline with a fast retriever …...

AbstractLexical substitution (LS) aims at finding appropriate substitutes for a target word in a sentence. Recently, LS methods based on pretrained language models have made remarkable progress, generating potential substitutes …...

AbstractContrastive Language–Image Pre-training (CLIP) has shown remarkable success in learning with cross-modal supervision from extensive amounts of image–text pairs collected online. Thus far, the effectiveness of CLIP has been investigated …...

AbstractGenerating free-text rationales is a promising step towards explainable NLP, yet evaluating such rationales remains a challenge. Existing metrics have mostly focused on measuring the association between the rationale and …...

AbstractOpen Information Extraction (OpenIE) has been used in the pipelines of various NLP tasks. Unfortunately, there is no clear consensus on which models to use in which tasks. Muddying things …...