Metrics
Related Papers
Pseudo Relevance Feedback Using Named Entities for Question Answering
Relevance feedback has already proven its usefulness in probabilistic information re- trieval (IR). In this research we explore whether a pseudo relevance feedback tech- nique on IR can improve the …...
Findings of the 2009 Workshop on Statistical Machine Translation
This paper presents the results of the WMT09 shared tasks, which included a translation task, a system combination task, and an evaluation task. We con- ducted a large-scale manual evaluation …...
Non-Parametric Bayesian Areal Linguistics
We describe a statistical model over linguis- tic areas and phylogeny. Our model recov- ers known areas and identifies a plausible hi- erarchy of areal features. The use of areas …...
Discovering Diverse and Salient Threads in Document Collections
We propose a novel probabilistic technique for modeling and extracting salient struc- ture from large document collections. As in clustering and topic modeling, our goal is to provide an organizing …...
Building a Dataset of Multilingual Cognates for the Romanian Lexicon
AbstractIdentifying cognates is an interesting task with applications in numerous research areas, such as historical and comparative linguistics, language acquisition, cross-lingual information retrieval, readability and machine translation. We propose a …...
Identification of Drug-Related Medical Conditions in Social Media
AbstractMonitoring social media has been shown to be an interesting approach for the early detection of drug adverse effects. In this paper, we describe a system which extracts medical entities …...
An Enhanced Knowledge Injection Model for Commonsense Generation
AbstractCommonsense generation aims at generating plausible everyday scenario description based on a set of provided concepts. Digging the relationship of concepts from scratch is non-trivial, therefore, we retrieve prototypes from …...
BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps
AbstractLearning to follow instructions is of fundamental importance to autonomous agents for vision-and-language navigation (VLN). In this paper, we study how an agent can navigate long paths when learning from …...
Multimodal Transformer for Multimodal Machine Translation
AbstractMultimodal Machine Translation (MMT) aims to introduce information from other modality, generally static images, to improve the translation quality. Previous works propose various incorporation methods, but most of them do …...
Probing Linguistic Systematicity
AbstractRecently, there has been much interest in the question of whether deep natural language understanding (NLU) models exhibit systematicity, generalizing such that units like words make consistent contributions to the …...
Semi-supervised Multi-task Learning for Multi-label Fine-grained Sexism Classification
AbstractSexism, a form of oppression based on one’s sex, manifests itself in numerous ways and causes enormous suffering. In view of the growing number of experiences of sexism reported online, …...
The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents
AbstractWe introduce dodecaDialogue: a set of 12 tasks that measures if a conversational agent can communicate engagingly with personality and empathy, ask questions, answer questions by utilizing knowledge resources, discuss …...
Knowledge Guided Metric Learning for Few-Shot Text Classification
AbstractHumans can distinguish new categories very efficiently with few examples, largely due to the fact that human beings can leverage knowledge obtained from relevant tasks. However, deep learning based text …...
Neural Language Modeling for Contextualized Temporal Graph Generation
AbstractThis paper presents the first study on using large-scale pre-trained language models for automated generation of an event-level temporal graph for a document. Despite the huge success of neural pre-training …...
On Generative Spoken Language Modeling from Raw Audio
AbstractWe introduce Generative Spoken Language Modeling, the task of learning the acoustic and linguistic characteristics of a language from raw audio (no text, no labels), and a set of metrics …...
Put Chatbot into Its Interlocutor’s Shoes: New Framework to Learn Chatbot Responding with Intention
AbstractMost chatbot literature that focuses on improving the fluency and coherence of a chatbot, is dedicated to making chatbots more human-like. However, very little work delves into what really separates …...
Scalable Font Reconstruction with Dual Latent Manifolds
AbstractWe propose a deep generative model that performs typography analysis and font reconstruction by learning disentangled manifolds of both font style and character shape. Our approach enables us to massively …...
Unsupervised Word Polysemy Quantification with Multiresolution Grids of Contextual Embeddings
AbstractThe number of senses of a given word, or polysemy, is a very subjective notion, which varies widely across annotators and resources. We propose a novel method to estimate polysemy …...
Cross-modal Contrastive Attention Model for Medical Report Generation
AbstractMedical report automatic generation has gained increasing interest recently as a way to help radiologists write reports more efficiently. However, this image-to-text task is rather challenging due to the typical …...
There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning
AbstractKnowledge-grounded dialogue (KGC) shows excellent potential to deliver an engaging and informative response. However, existing approaches emphasize selecting one golden knowledge given a particular dialogue context, overlooking the one-to-many phenomenon …...
A Practical Survey on Zero-Shot Prompt Design for In-Context Learning
AbstractThe remarkable advancements in large language models (LLMs) have brought about significant improvements in Natural Language Processing(NLP) tasks. This paper presents a comprehensive review of in-context learning techniques, focusing on …...
Conjunct Resolution in the Face of Verbal Omissions
AbstractVerbal omissions are complex syntactic phenomena in VP coordination structures. They occur when verbs and (some of) their arguments are omitted from subsequent clauses after being explicitly stated in an …...
On Prefix-tuning for Lightweight Out-of-distribution Detection
AbstractOut-of-distribution (OOD) detection, a fundamental task vexing real-world applications, has attracted growing attention in the NLP community. Recently fine-tuning based methods have made promising progress. However, it could be costly …...