Related papers: SC-Ques: A Sentence Completion Question Dataset fo…

Current neural query auto-completion (QAC) systems rely on character-level language models, but they slow down when queries are long. We present how to utilize subword language models for the fast and accurate generation of query completion…

We study textual autocomplete---the task of predicting a full sentence from a partial sentence---as a human-machine communication game. Specifically, we consider three competing goals for effective communication: use as few tokens as…

We introduce a new reading comprehension dataset, dubbed MultiWikiQA, which covers 306 languages and has 1,220,757 samples in total. We start with Wikipedia articles, which also provide the context for the dataset samples, and use an LLM to…

We propose Blank Language Model (BLM), a model that generates sequences by dynamically creating and filling in blanks. The blanks control which part of the sequence to expand, making BLM ideal for a variety of text editing and rewriting…

Query auto-completion is a search engine feature whereby the system suggests completed queries as the user types. Recently, the use of a recurrent neural network language model was suggested as a method of generating query completions. We…

Within the big data tsunami, relational databases and SQL are still there and remain mandatory in most of cases for accessing data. On the one hand, SQL is easy-to-use by non specialists and allows to identify pertinent initial data at the…

Nowadays, training end-to-end neural models for spoken language translation (SLT) still has to confront with extreme data scarcity conditions. The existing SLT parallel corpora are indeed orders of magnitude smaller than those available for…

This paper introduces the first dataset for evaluating English-Chinese Bilingual Contextual Word Similarity, namely BCWS (https://github.com/MiuLab/BCWS). The dataset consists of 2,091 English-Chinese word pairs with the corresponding…

Sentence fusion is the task of joining several independent sentences into a single coherent text. Current datasets for sentence fusion are small and insufficient for training modern neural models. In this paper, we propose a method for…

While contextualized word embeddings have been a de-facto standard, learning contextualized phrase embeddings is less explored and being hindered by the lack of a human-annotated benchmark that tests machine understanding of phrase…

Recent state-of-the-art natural language understanding models, such as BERT and XLNet, score a pair of sentences (A and B) using multiple cross-attention operations - a process in which each word in sentence A attends to all words in…

Both humans and machines learn the meaning of unknown words through contextual information in a sentence, but not all contexts are equally helpful for learning. We introduce an effective method for capturing the level of contextual…

The adoption of large language models (LLMs) to assist clinicians has attracted remarkable attention. Existing works mainly adopt the close-ended question-answering (QA) task with answer options for evaluation. However, many clinical…

Computing universal distributed representations of sentences is a fundamental task in natural language processing. We propose ConsSent, a simple yet surprisingly powerful unsupervised method to learn such representations by enforcing…

We introduce a high-quality dataset that contains 3,397 samples comprising (i) multiple choice questions, (ii) answers (including distractors), and (iii) their source documents, from the educational domain. Each question is phrased in two…

Sentence simplification tends to focus on the generic simplification of sentences by making them more readable and easier to understand. This paper provides a dataset aimed at training models that perform subject aware sentence…

Human knowledge is collectively encoded in the roughly 6500 languages spoken around the world, but it is not distributed equally across languages. Hence, for information-seeking question answering (QA) systems to adequately serve speakers…

Large language models (LLMs) have shown remarkable performance across various sentence-based linguistic phenomena, yet their ability to capture cross-sentence paradigmatic patterns, such as verb alternations, remains underexplored. In this…

Developing an educational test can be expensive and time-consuming, as each item must be written by experts and then evaluated by collecting hundreds of student responses. Moreover, many tests require multiple distinct sets of questions…

Conversion of spoken mathematical expressions is a challenging task that involves transcribing speech into a strictly structured symbolic representation while addressing the ambiguity inherent in the pronunciation of equations. Although…