Related papers: PoMo: Generating Entity-Specific Post-Modifiers in…
Understanding the speaker's intended meaning often involves drawing commonsense inferences to reason about what is not stated explicitly. In multi-event sentences, it requires understanding the relationships between events based on…
Paraphrase generation is a longstanding important problem in natural language processing. In addition, recent progress in deep generative models has shown promising results on discrete latent variables for text generation. Inspired by…
We encounter arguments everyday in the form of social media posts, presidential debates, news articles, and even advertisements. A ubiquitous, influential example is the opinion piece (op-ed). Opinion pieces can provide valuable…
To sustain engaging conversation, it is critical for chatbots to make good use of relevant knowledge. Equipped with a knowledge base, chatbots are able to extract conversation-related attributes and entities to facilitate context modeling…
Writers generally rely on plans or sketches to write long stories, but most current language models generate word by word from left to right. We explore coarse-to-fine models for creating narrative texts of several hundred words, and…
Recent approaches to data-to-text generation have shown great promise thanks to the use of large-scale datasets and the application of neural network architectures which are trained end-to-end. These models rely on representation learning…
Recently, pretrained language models (PLMs) have had exceptional success in language generation. To leverage the rich knowledge encoded by PLMs, a simple yet powerful paradigm is to use prompts in the form of either discrete tokens or…
Traditional semantic similarity models often fail to encapsulate the external context in which texts are situated. However, textual datasets generated on mobile platforms can help us build a truer representation of semantic similarity by…
With the remarkable development of large language models (LLMs), ensuring the factuality of output has become a challenge. However, having all the contents of the response with given knowledge or facts is not necessarily a good thing in…
There is a growing interest in designing autonomous agents that can work alongside humans. Such agents will undoubtedly be expected to explain their behavior and decisions. While generating explanations is an actively researched topic, most…
The alt-text generation task produces concise, context-relevant descriptions of images, enabling blind and low-vision users to access online images. Despite the capabilities of large vision-language models, alt-text generation performance…
Understanding a long document requires tracking how entities are introduced and evolve over time. We present a new type of language model, EntityNLM, that can explicitly model entities, dynamically update their representations, and…
Existing 3D human motion generation and understanding methods often exhibit limited interpretability, restricting effective mutual enhancement between these inherently related tasks. While current unified frameworks based on large language…
Citation sentimet analysis is one of the little studied tasks for scientometric analysis. For citation analysis, we developed eight datasets comprising citation sentences, which are manually annotated by us into three sentiment polarities…
Conventional algorithms for training language models (LMs) with human feedback rely on preferences that are assumed to account for an "average" user, disregarding subjectivity and finer-grained variations. Recent studies have raised…
We study the problem of few-shot Fine-grained Entity Typing (FET), where only a few annotated entity mentions with contexts are given for each entity type. Recently, prompt-based tuning has demonstrated superior performance to standard…
The advancement of Large Language Models (LLMs) has enabled their application in personalized dialogue systems. We present an extended annotation scheme for personal fact classification that addresses limitations in existing approaches,…
Existing dense or paragraph video captioning approaches rely on holistic representations of videos, possibly coupled with learned object/action representations, to condition hierarchical language decoders. However, they fundamentally lack…
In order to simplify a sentence, human editors perform multiple rewriting transformations: they split it into several shorter sentences, paraphrase words (i.e. replacing complex words or phrases by simpler synonyms), reorder components,…
Semantically meaningful sentence embeddings are important for numerous tasks in natural language processing. To obtain such embeddings, recent studies explored the idea of utilizing synthetically generated data from pretrained language…