Search Results for author:
Found 81 papers, 25 papers with code
Open-Domain Contextual Link Prediction and its Complementarity with Entailment Graphs
In this paper, we introduce the new task of open-domain contextual link prediction which has access to both the textual context and the KG structure to perform link prediction.
Mastering the Craft of Data Synthesis for CodeLLMs
Large language models (LLMs) have shown impressive performance in \emph{code} understanding and generation, making coding tasks a key focus for researchers due to their practical applications and value as a testbed for LLM evaluation.
A Language-agnostic Model of Child Language Acquisition
This work reimplements a recent semantic bootstrapping child-language acquisition model, which was originally designed for English, and trains it to learn a new language: Hebrew.
Sources of Hallucination by Large Language Models on Inference Tasks
Large Language Models (LLMs) are claimed to be capable of Natural Language Inference (NLI), necessary for applied tasks like question answering and summarization.
Smoothing Entailment Graphs with Language Models
The diversity and Zipfian frequency distribution of natural language predicates in corpora leads to sparsity in Entailment Graphs (EGs) built by Open Relation Extraction (ORE).
Three-dimensional Cooperative Localization of Commercial-Off-The-Shelf Sensors
We propose an efficient approach to solve the corresponding permutation combinatorial optimization problem, which integrates continuous space cooperative localization and permutation space likelihood ascent search.
Blindness to Modality Helps Entailment Graph Mining
Understanding linguistic modality is widely seen as important for downstream tasks such as Question Answering and Knowledge Graph Population.
Incorporating Temporal Information in Entailment Graph Mining
We present a novel method for injecting temporality into entailment graphs to address the problem of spurious entailments, which may arise from similar but temporally distinct events involving the same pair of entities.
Mention Flags (MF): Constraining Transformer-based Text Generators
In this paper, we propose Mention Flags (MF), which traces whether lexical constraints are satisfied in the generated outputs in an S2S decoder.
Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation
Sequence-to-Sequence (S2S) neural text generation models, especially the pre-trained ones (e. g., BART and T5), have exhibited compelling performance on various natural language generation tasks.
Integrating Lexical Information into Entity Neighbourhood Representations for Relation Prediction
OpenKi[1] addresses this task through extraction of named entities and predicates via OpenIE tools then learning relation embeddings from the resulting entity-relation graph for relation prediction, outperforming previous approaches.
Multivalent Entailment Graphs for Question Answering
Drawing inferences between open-domain natural language predicates is a necessity for true language understanding.
There and Back Again: Self-supervised Multispectral Correspondence Estimation
In this work, we aim to address the dense correspondence estimation problem in a way that generalizes to more than one spectrum.
ECOL-R: Encouraging Copying in Novel Object Captioning with Reinforcement Learning
In this paper, we focus on this challenge and propose the ECOL-R model (Encouraging Copying of Object Labels with Reinforced Learning), a copy-augmented transformer model that is encouraged to accurately describe the novel object labels.
Detecting and Exorcising Statistical Demons from Language Models with Anti-Models of Negative Data
Indeed, self-supervised language models trained on "positive" examples of English text generalize in desirable ways to many natural language tasks.
End-to-End Speech Recognition and Disfluency Removal
Disfluency detection is usually an intermediate step between an automatic speech recognition (ASR) system and a downstream task.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Low-Complexity System and Algorithm for an Emergency Ventilator Sensor and Alarm
In response to the shortage of ventilators caused by the COVID-19 pandemic, many organizations have designed low-cost emergency ventilators.
Improving Disfluency Detection by Self-Training a Self-Attentive Model
However, we show that self-training - a semi-supervised technique for incorporating unlabeled data - sets a new state-of-the-art for the self-attentive parser on disfluency detection, demonstrating that self-training provides benefits orthogonal to the pre-trained contextualized word representations.
Duality of Link Prediction and Entailment Graph Induction
The new entailment score outperforms prior state-of-the-art results on a standard entialment dataset and the new link prediction scores show improvements over the raw link prediction scores.
An adaptable task-oriented dialog system for stand-alone embedded devices
This paper describes a spoken-language end-to-end task-oriented dialogue system for small embedded devices such as home appliances.
How to best use Syntax in Semantic Role Labelling
There are many different ways in which external information might be used in an NLP task.
Neural Constituency Parsing of Speech Transcripts
This paper studies the performance of a neural self-attentive parser on transcribed speech.
nocaps: novel object captioning at scale
To encourage the development of image captioning models that can learn visual concepts from alternative data sources, such as object detection datasets, we present the first large-scale benchmark for this task.
Improving Topic Models with Latent Feature Word Representations
Probabilistic topic models are widely used to discover latent topics in document collections, while latent feature vector representations of words have been used to obtain high performance in many NLP tasks.
Disfluency Detection using a Noisy Channel Model and a Deep Neural Language Model
This paper presents a model for disfluency detection in spontaneous speech transcripts called LSTM Noisy Channel Model.
Disfluency Detection using Auto-Correlational Neural Networks
In recent years, the natural language processing community has moved away from task-specific feature engineering, i. e., researchers discovering ad-hoc feature representations for various tasks, in favor of general-purpose methods that learn the input representation by themselves.
Predicting accuracy on large datasets from smaller pilot data
Because obtaining training data is often the most difficult part of an NLP or ML project, we develop methods for predicting how much data is required to achieve a desired test accuracy by extrapolating results from models trained on a small pilot training dataset.
Active learning for deep semantic parsing
Semantic parsing requires training data that is expensive and slow to collect.
Partially-Supervised Image Captioning
To address this problem, we teach image captioning models new visual concepts from labeled images and object detection datasets.
AMR Dependency Parsing with a Typed Semantic Algebra
We present a semantic parser for Abstract Meaning Representations which learns to parse strings into tree representations of the compositional structure of an AMR graph.
VnCoreNLP: A Vietnamese Natural Language Processing Toolkit
We present an easy-to-use and fast toolkit, namely VnCoreNLP---a Java NLP annotation pipeline for Vietnamese.
Learning Typed Entailment Graphs with Global Soft Constraints
We instead propose a scalable method that learns globally consistent similarity scores based on new soft constraints that consider both the structures across typed entailment graphs and inside each graph.
Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments
This is significant because a robot interpreting a natural-language navigation instruction on the basis of what it sees is carrying out a vision and language process that is similar to Visual Question Answering.
Ranked #10 on
Visual Navigation
on R2R
From Word Segmentation to POS Tagging for Vietnamese
This paper presents an empirical comparison of two strategies for Vietnamese Part-of-Speech (POS) tagging from unsegmented text: (i) a pipeline strategy where we consider the output of a word segmenter as the input of a POS tagger, and (ii) a joint strategy where we predict a combined segmentation and POS tag for each syllable.
A Fast and Accurate Vietnamese Word Segmenter
We propose a novel approach to Vietnamese word segmentation.
Multilingual Semantic Parsing And Code-Switching
As far as we know, this is the first study of code-switching in semantic parsing.
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning.
Ranked #29 on
Visual Question Answering (VQA)
on VQA v2 test-std
Unsupervised Text Segmentation Based on Native Language Characteristics
Most work on segmenting text does so on the basis of topic changes, but it can be of interest to segment by other, stylistically expressed characteristics such as change of authorship or native language.
Idea density for predicting Alzheimer's disease from transcribed speech
ID has been used in two different versions: propositional idea density (PID) counts the expressed ideas and can be applied to any text while semantic idea density (SID) counts pre-defined information content units and is naturally more applicable to normative domains, such as picture description tasks.
A Novel Neural Network Model for Joint POS Tagging and Graph-based Dependency Parsing
We present a novel neural network model that learns POS tagging and graph-based dependency parsing jointly.
Ranked #5 on
Part-Of-Speech Tagging
on UD
Search Personalization with Embeddings
Recent research has shown that the performance of search personalization depends on the richness of user profiles which normally represent the user's topical interests.
Guided Open Vocabulary Image Captioning with Constrained Beam Search
Existing image captioning models do not generalize well to out-of-domain images containing novel scenes or objects.
Grammar induction from (lots of) words alone
We show that grammar induction from words alone is in fact feasible when the model is provided with sufficient training data, and present two new streaming or mini-batch algorithms for PCFG inference that can learn from millions of words of training data.
An empirical study for Vietnamese dependency parsing
This paper presents an empirical comparison of different dependency parsers for Vietnamese, which has some unusual characteristics such as copula drop and verb serialization.
SPICE: Semantic Propositional Image Caption Evaluation
There is considerable interest in the task of automatically generating image captions.
STransE: a novel embedding model of entities and relationships in knowledge bases
Knowledge bases of real-world facts about entities and their relationships are useful resources for a variety of natural language processing tasks.
Neighborhood Mixture Model for Knowledge Base Completion
Knowledge bases are useful resources for many natural language processing tasks, however, they are far from complete.
Bridging the gap between speech technology and natural language processing: an evaluation toolbox for term discovery systems
The unsupervised discovery of linguistic terms from either continuous phoneme transcriptions or from raw speech has seen an increasing interest in the past years both from a theoretical and a practical standpoint.
Exploring the Role of Stress in Bayesian Word Segmentation using Adaptor Grammars
Stress has long been established as a major cue in word segmentation for English infants.
Joint Incremental Disfluency Detection and Dependency Parsing
We present an incremental dependency parsing model that jointly performs disfluency detection.
Parsing entire discourses as very long strings: Capturing topic continuity in grounded language learning
Grounded language learning, the task of mapping from natural language to a representation of meaning, has attracted more and more interest in recent years.
Synergies in learning words and their referents
This paper presents Bayesian non-parametric models that simultaneously learn to segment words from phoneme strings and learn the referents of some of those words, and shows that there is a synergistic interaction in the acquisition of these two kinds of linguistic information.
