Articles

In this paper, we introduce an event-driven trading strategy that predicts stock movements by detecting corporate events from news arti- cles. Unlike existing models that utilize tex- tual features (e.g., bag-of-words) and senti- ments to directly make stock predictions, we consider corporate events as the driving force behind stock movements …...

The advent of large pre-trained language mod- els has made it possible to make high-quality predictions on how to add or change a sentence in a document. However, the high branching factor inherent to text generation impedes the ability of even the strongest language models to offer useful editing suggestions …...

ICD coding aims to automatically assign Inter- national Classification of Diseases (ICD) codes from unstructured clinical notes or discharge summaries, which saves human labor and re- duces errors. Although several studies are pro- posed to solve this challenging task, none dis- tinguishes the importance of different phrases with a word …...

Understanding what we genuinely mean in- stead of what we literally say in conversations is challenging for both humans and machines; yet, this direction is mostly left untouched in modern open-ended dialogue systems. To fill in this gap, we present a grammar-based dia- logue dataset, GRICE, designed to bring impli- …...

Previous studies have argued that pre-trained language models encode commonsense rela- tional knowledge (e.g. that apples are ed- ible). However, simultaneous work has re- vealed that such models are often insensitive to context, even ignoring overt contextual cues such as negations. In this paper, we investigate whether masked language models …...

We present Language-mediated, Object- centric Representation Learning (LORL), a paradigm for learning disentangled, object- centric scene representations from vision and language. LORL builds upon recent advances in unsupervised object discovery and segmen- tation, notably MONet and Slot Attention. While these algorithms learn an object-centric representation just by reconstructing the input …...

Because sign language is a visual language, the translation of it into spoken language is typically performed through an intermediate representation called gloss notation. In sign language, function words, such as particles and determiners, are not explicitly expressed, and there is little or no concept of morpho- logical inflection in …...

In Natural Language Understanding (NLU), to facilitate Cross-Lingual Transfer Learning (CLTL), especially CLTL between distant lan- guages, we integrate CLTL with Machine Translation (MT), and thereby propose a novel CLTL model named Translation Aided Lan- guage Learner (TALL). TALL is constructed as a standard transformer, where the encoder is a …...

Screenplays refer to characters using differ- ent names, pronouns, and nominal expres- sions. We need to resolve these mentions to the correct referent character for better story understanding and holistic research in compu- tational narratology. Coreference resolution of character mentions in screenplays becomes challenging because of the large document lengths, …...

Retrofitting is a technique used to move word vectors closer together or further apart in their space to reflect their relationships in a Knowl- edge Base (KB). However, retrofitting only works on concepts that are present in that KB. RetroGAN uses a pair of Generative Ad- versarial Networks (GANs) to …...

Language modeling (LM) for automatic speech recognition (ASR) does not usually in- corporate utterance level contextual informa- tion. For some domains like voice assistants, however, additional context, such as time at which an utterance was spoken, provides a rich input signal. We introduce an attention mechanism for training neural speech …...

We introduce categorical modularity, a novel low-resource intrinsic metric to evaluate word embedding quality. Categorical modularity is a graph modularity metric based on the k-near- est neighbor graph constructed with embed- ding vectors of words from a fixed set of se- mantic categories, in which the goal is to mea- …...

We study calibration in question answering, es- timating whether model correctly predicts an- swer for each question. Unlike prior work which mainly rely on the model’s confidence score, our calibrator incorporates information about the input example (e.g., question and the evidence context). Together with data aug- mentation via back translation, …...

We consider a joint information extraction (IE) model, solving named entity recognition, coreference resolution and relation extraction jointly over the whole document. In particu- lar, we study how to inject information from a knowledge base (KB) in such IE model, based on unsupervised entity linking. The used KB entity representations …...

Learning disentangled representations of texts, which encode information pertaining to differ- ent aspects of the text in separate representa- tions, is an active area of research in NLP for controllable and interpretable text generation. These methods have, for the most part, been developed in the context of text style transfer, …...

This paper presents a comparison of unsuper- vised methods of hypernymy prediction (i.e., to predict which word in a pair of words such as fish–cod is the hypernym and which the hy- ponym). Most importantly, we demonstrate across datasets for English and for German that the predictions of three methods …...

Existing Natural Language Understanding (NLU) models have been shown to incorporate dataset biases leading to strong performance on in-distribution (ID) test sets but poor per- formance on out-of-distribution (OOD) ones. We introduce a simple yet effective debias- ing framework whereby the shallow represen- tations of the main model are used …...

We propose a study of the development of scientific topics through time, as well as the relations between them within the scientific field of computational linguistics and across subfields. We use topic modeling to analyze scientific texts published in the ACL Anthol- ogy, and introduce a categorization of topics in …...

Accurate detection and classification of online hate is a difficult task. Implicit hate is particu- larly challenging as such content tends to have unusual syntax, polysemic words, and fewer markers of prejudice (e.g., slurs). This prob- lem is heightened with multimodal content, such as memes (combinations of text and im- …...

This paper studies the end-to-end construction of an NLP Knowledge Graph (KG) from scien- tific papers. We focus on extracting four types of relations: evaluatedOn between tasks and datasets, evaluatedBy between tasks and eval- uation metrics, as well as coreferent and re- lated relations between the same type of en- …...