In this paper, we study the task of instructional dialogue and focus on ...
Style is used to convey authors' intentions and attitudes. Despite the
s...
Recent progress in domain adaptation for coreference resolution relies o...
In this paper, we explore the question of whether language models (LLMs)...
Fine-tuning large models is highly effective, however, inference using t...
Large language models have demonstrated an emergent capability in answer...
Named Entity Recognition (NER) is an important and well-studied task in
...
We present a human-in-the-loop evaluation framework for fact-checking no...
Translating training data into many languages has emerged as a practical...
We present Stanceosaurus, a new corpus of 28,033 tweets in English, Hind...
Anaphora resolution is an important task for information extraction acro...
In this paper we present SynKB, an open-source, automatically extracted
...
Recent work has demonstrated that pre-training in-domain language models...
Dialogue models trained on human conversations inadvertently learn to
ge...
We develop Process Execution Graphs (PEG), a document-level representati...
This paper presents the results of the wet lab information extraction ta...
Transformers that are pre-trained on multilingual text corpora, such as,...
We present a corpus of 7,500 tweets annotated with COVID-19 events, incl...
Question answering (QA) is an important aspect of open-domain conversati...
There is an increasing interest in studying natural language and compute...
The Arabic language is a morphological rich language, posing many challe...
In recent years, sentiment analysis in social media has attracted a lot ...
We describe the Sentiment Analysis in Twitter task, ran as part of
SemEv...
In this paper, we describe the 2015 iteration of the SemEval shared task...
This paper discusses the fourth year of the “Sentiment Analysis in Twitt...
We present an approach to minimally supervised relation extraction that
...
Breaking cybersecurity events are shared across a range of websites,
inc...
Neural conversation models tend to generate safe, generic responses for ...
We describe an effort to annotate a corpus of natural language instructi...
Social media users often make explicit predictions about upcoming events...
In this paper, drawing intuition from the Turing test, we propose using
...
We describe TweeTIME, a temporal tagger for recognizing and normalizing ...
Recent neural models of dialogue generation offer great promise for
gene...
Inferring latent attributes of people online is an important social comp...
We propose a framework for inferring the latent attitudes or preferences...