Related papers: A Mention-Ranking Model for Abstract Anaphora Reso…
Contextual ASR, which takes a list of bias terms as input along with audio, has drawn recent interest as ASR use becomes more widespread. We are releasing contextual biasing lists to accompany the Earnings21 dataset, creating a public…
Enormous explosion in the number of the World Wide Web pages occur every day and since the efficiency of most of the information processing systems is found to be less, the potential of the Internet applications is often underutilized.…
Abstractive text summarization is one of the areas influenced by the emergence of pre-trained language models. Current pre-training works in abstractive summarization give more points to the summaries with more words in common with the main…
Large language models (LLMs) have achieved remarkable performance in generating human-like text and solving reasoning tasks of moderate complexity, such as question-answering and mathematical problem-solving. However, their capabilities in…
Metaphors are ubiquitous in human language. The metaphor detection task (MD) aims at detecting and interpreting metaphors from written language, which is crucial in natural language understanding (NLU) research. In this paper, we introduce…
Abstract Meaning Representation (AMR) represents sentences as directed, acyclic and rooted graphs, aiming at capturing their meaning in a machine readable format. AMR parsing converts natural language sentences into such graphs. However,…
Previous work on bridging anaphora recognition (Hou et al., 2013a) casts the problem as a subtask of learning fine-grained information status (IS). However, these systems heavily depend on many hand-crafted linguistic features. In this…
We introduce ASQ, a tool to automatically mine questions and answers from a sentence using the Abstract Meaning Representation (AMR). Previous work has used question-answer pairs to specify the predicate-argument structure of a sentence…
We present an approach to anaphora resolution based on a focusing algorithm, and implemented within an existing MUC (Message Understanding Conference) Information Extraction system, allowing quantitative evaluation against a substantial…
Image and sentence matching has made great progress recently, but it remains challenging due to the large visual-semantic discrepancy. This mainly arises from that the representation of pixel-level image usually lacks of high-level semantic…
Recent models for unsupervised representation learning of text have employed a number of techniques to improve contextual word representations but have put little focus on discourse-level representations. We propose CONPONO, an…
Analogical inference is a remarkable capability of human reasoning, and has been used to solve hard reasoning tasks. Analogy based reasoning (AR) has gained increasing interest from the artificial intelligence community and has shown its…
Existing discourse corpora are annotated based on different frameworks, which show significant dissimilarities in definitions of arguments and relations and structural constraints. Despite surface differences, these frameworks share basic…
We propose and study a novel supervised approach to learning statistical semantic relatedness models from subjectively annotated training examples. The proposed semantic model consists of parameterized co-occurrence statistics associated…
Pre-trained language models have made great progress on dialogue tasks. However, these models are typically trained on surface dialogue text, thus are proven to be weak in understanding the main semantic meaning of a dialogue context. We…
We review the task of Sentence Pair Scoring, popular in the literature in various forms - viewed as Answer Sentence Selection, Semantic Text Scoring, Next Utterance Ranking, Recognizing Textual Entailment, Paraphrasing or e.g. a component…
This paper describes a standalone, publicly-available implementation of the Resolution of Anaphora Procedure (RAP) given by Lappin and Leass (1994). The RAP algorithm resolves third person pronouns, lexical anaphors, and identifies…
Metaphors are ubiquitous in natural language, and their detection plays an essential role in many natural language processing tasks, such as language understanding, sentiment analysis, etc. Most existing approaches for metaphor detection…
As Abstract Meaning Representation (AMR) implicitly involves compound semantic annotations, we hypothesize auxiliary tasks which are semantically or formally related can better enhance AMR parsing. We find that 1) Semantic role labeling…
In continual learning, a system learns from non-stationary data streams or batches without catastrophic forgetting. While this problem has been heavily studied in supervised image classification and reinforcement learning, continual…