Search Results for author:
Found 188 papers, 81 papers with code
Effective Fine-Tuning Methods for Cross-lingual Adaptation
In this work, we propose a novel fine-tuning method based on co-training that aims to learn more generalized semantic equivalences as a complementary to multilingual language modeling using the unlabeled data in the target language.
Response Selection for Multi-Party Conversations with Dynamic Topic Tracking
While participants in a multi-party multi-turn conversation simultaneously engage in multiple conversation topics, existing response selection methods are developed mainly focusing on a two-party single-conversation scenario.
LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs
We present the first systematic evaluation examining format bias in performance of large language models (LLMs).
DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts
Data-driven storytelling is a powerful method for conveying insights by combining narrative techniques with visualizations and text.
A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations
To address this, we systematically review the primary challenges and limitations causing these inconsistencies and unreliable evaluations in various steps of LLM evaluation.
ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild
However, existing methods suffer crucial drawbacks across two critical axes affecting the performance of chart representation models: they are trained on data generated from underlying data tables of the charts, ignoring the visual trends and patterns in chart images, and use weakly aligned vision-language backbone models for domain-specific training, limiting their generalizability when encountering charts in the wild.
XL-HeadTags: Leveraging Multimodal Retrieval Augmentation for the Multilingual Generation of News Headlines and Tags
Millions of news articles published online daily can overwhelm readers.
Decompose and Aggregate: A Step-by-Step Interpretable Evaluation Framework
The acceleration of Large Language Models (LLMs) research has opened up new possibilities for evaluating generated texts.
Prompt Leakage effect and defense strategies for multi-turn LLM interactions
We measure the mitigation effect of 7 black-box defense strategies, along with finetuning an open-source model to defend against leakage attempts.
Relevant or Random: Can LLMs Truly Perform Analogical Reasoning?
One key finding in psychology is that compared with irrelevant past experiences, recalling relevant ones can help humans better handle new tasks.
Lifelong Event Detection with Embedding Space Separation and Compaction
However, the simple combination of memory data and new-task samples can still result in substantial forgetting of previously acquired knowledge, which may occur due to the potential overlap between the feature distribution of new data and the previously learned embedding space.
ParaICL: Towards Robust Parallel In-Context Learning
However, our preliminary experiments indicate that the effectiveness of ICL is limited by the length of the input context.
How Much are Large Language Models Contaminated? A Comprehensive Survey and the LLMSanitize Library
With the rise of Large Language Models (LLMs) in recent years, abundant new opportunities are emerging, but also new challenges, among which contamination is quickly becoming critical.
From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models
This survey paper serves as a comprehensive resource for researchers and practitioners in the fields of natural language processing, computer vision, and data analysis, providing valuable insights and directions for future research in chart understanding leveraging large foundation models.
ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning
Further evaluation shows that our instruction-tuning approach supports a wide array of real-world chart comprehension and reasoning scenarios, thereby expanding the scope and applicability of our models to new kinds of tasks.
Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges
In the rapidly evolving field of large language models (LLMs), data augmentation (DA) has emerged as a pivotal technique for enhancing model performance by diversifying training examples without the need for additional data collection.
Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing
Large Language Models (LLMs) have demonstrated significant potential in handling complex reasoning tasks through step-by-step rationale generation.
BootPIG: Bootstrapping Zero-shot Personalized Image Generation Capabilities in Pretrained Diffusion Models
We propose a novel architecture (BootPIG) that allows a user to provide reference images of an object in order to guide the appearance of a concept in the generated images.
Improving In-context Learning via Bidirectional Alignment
Large language models (LLMs) have shown impressive few-shot generalization on many tasks via in-context learning (ICL).
Do LLMs Work on Charts? Designing Few-Shot Prompts for Chart Question Answering and Summarization
However, their application to chart-related tasks is not trivial as these tasks typically involve considering not only the underlying data but also the visual features in the chart image.
X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning
To enable this framework, we devise a scalable pipeline that automatically generates high-quality, instruction-tuning datasets from readily available captioning data across different modalities, and contribute 24K QA data for audio and 250K QA data for 3D.
ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?
Upon its release in late 2022, ChatGPT has brought a seismic shift in the entire landscape of AI, both in research and commerce.
Diffusion Model Alignment Using Direct Preference Optimization
Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences.
Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization
Our study reveals that instruction controllable text summarization remains a challenging task for LLMs, since (1) all LLMs evaluated still make factual and other types of errors in their summaries; (2) no LLM-based evaluation methods can achieve a strong alignment with human annotators when judging the quality of candidate summaries; (3) different LLMs show large performance gaps in summary generation and evaluation capabilities.
DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text
Moreover, a significant gap in the current landscape is the absence of a realistic benchmark for evaluating the effectiveness of grounding LLMs on heterogeneous knowledge sources (e. g., knowledge base and text).
Personalised Distillation: Empowering Open-Sourced LLMs with Adaptive Learning for Code Generation
With the rise of powerful closed-sourced LLMs (ChatGPT, GPT-4), there are increasing interests in distilling the capabilies of close-sourced LLMs to smaller open-sourced LLMs.
Ranked #58 on
Code Generation
on HumanEval
On Context Utilization in Summarization with Large Language Models
In this paper, we conduct the first comprehensive study on context utilization and position bias in summarization.
Lifelong Sequence Generation with Dynamic Module Expansion and Adaptation
Inspired by the learning paradigm of humans, we propose Dynamic Module Expansion and Adaptation (DMEA), which enables the model to dynamically determine the architecture for acquiring new knowledge based on task correlation and select the most similar previous tasks to facilitate adaptation to new tasks.
CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules
We find that by naturally encouraging the LLM to reuse the previously developed and verified sub-modules, CodeChain can significantly boost both modularity as well as correctness of the generated solutions, achieving relative pass@1 improvements of 35% on APPS and 76% on CodeContests.
Ranked #3 on
Code Generation
on CodeContests
Hierarchical Evaluation Framework: Best Practices for Human Evaluation
Human evaluation plays a crucial role in Natural Language Processing (NLP) as it assesses the quality and relevance of developed systems, thereby facilitating their enhancement.
L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models
Recently, large language models (LLMs), especially those that are pretrained on code, have demonstrated strong capabilities in generating programs from natural language inputs in a few-shot or even zero-shot manner.
Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles
In this paper, we propose a new task of summarizing diverse information encountered in multiple news articles encompassing the same event.
RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair
Automatic program repair (APR) is crucial to reduce manual debugging efforts for developers and improve software reliability.
XGen-7B Technical Report
Most open-source LLMs, on the other hand, are limited in their ability to support longer sequence lengths, which is a key requirement for many tasks that require inference over an input context.
Modeling Uncertainty and Using Post-fusion as Fallback Improves Retrieval Augmented Generation with LLMs
This paper aims to fill this gap by investigating different methods of combining retrieved passages with LLMs to enhance answer generation.
PromptSum: Parameter-Efficient Controllable Abstractive Summarization
Prompt tuning (PT), a parameter-efficient technique that only tunes the additional prompt embeddings while keeping the backbone pre-trained language model (PLM) frozen, has shown promising results in language understanding tasks, especially in low-resource scenarios.
Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts
Large language models (LLMs) are known to effectively perform tasks by simply observing few exemplars.
Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning
Large language models (LLMs) have shown impressive performance in following natural language instructions to solve unseen tasks.
Building Extractive Question Answering System to Support Human-AI Health Coaching Model for Sleep Domain
Non-communicable diseases (NCDs) are a leading cause of global deaths, necessitating a focus on primary prevention and lifestyle behavior change.
SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pages
Text simplification research has mostly focused on sentence-level simplification, even though many desirable edits - such as adding relevant background information or reordering content - may require document-level context.
A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets
The development of large language models (LLMs) such as ChatGPT has brought a lot of attention recently.
Ranked #8 on
Natural Language Inference
on ANLI test
Unlocking Temporal Question Answering for Large Language Models Using Code Execution
Our preliminary experiments show that generating intermediate reasoning steps does not always boost the performance of complex temporal question-answering tasks.
UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning
Charts are very popular for analyzing data, visualizing key insights and answering complex reasoning questions about data.
Ranked #18 on
Chart Question Answering
on ChartQA
(using extra training data)
LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond
To address this, we propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits.
Exploring Self-supervised Logic-enhanced Training for Large Language Models
Existing efforts to improve logical reasoning ability of language models have predominantly relied on supervised fine-tuning, hindering generalization to new domains and/or tasks.
Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources
Specifically, CoK consists of three stages: reasoning preparation, dynamic knowledge adapting, and answer consolidation.
Randomized Smoothing with Masked Inference for Adversarially Robust Text Classifications
Large-scale pre-trained language models have shown outstanding performance in a variety of NLP tasks.
Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework
As large language models (LLMs) have become the norm in NLP, demonstrating good performance in generation and reasoning tasks, one of its most fatal disadvantages is the lack of factual correctness.
Modeling What-to-ask and How-to-ask for Answer-unaware Conversational Question Generation
In addition, we propose Conv-Distinct, a novel evaluation metric for CQG, to evaluate the diversity of the generated conversation from a context.
Explaining Language Models' Predictions with High-Impact Concepts
The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions.
Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning
Our results demonstrate the strong and efficient modeling ability of NLI-based classifiers and the large cross-lingual transfer improvements achieved by our aligned prompts, particularly in few-shot settings.
A Data-centric Framework for Improving Domain-specific Machine Reading Comprehension Datasets
We applied the proposed framework to four biomedical datasets and showed relative improvement of up to 33%/40% for fine-tuning of retrieval/reader models on the BioASQ dataset when using back translation to enhance the original dataset quality.
Retrieving Multimodal Information for Augmented Generation: A Survey
As Large Language Models (LLMs) become popular, there emerged an important trend of using multimodality to augment the LLMs' generation ability, which enables LLMs to better interact with the world.
Towards Interpretable and Efficient Automatic Reference-Based Summarization Evaluation
Interpretability and efficiency are two important considerations for the adoption of neural automatic metrics.
xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval
Recently, pre-trained large language models (LLMs) have shown impressive abilities in generating codes from natural language descriptions, repairing buggy codes, translating codes between languages, and retrieving relevant code segments.
Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?
Despite this, PT has been shown to rely heavily on good initialization of the prompt embeddings.
Dynamic Scheduled Sampling with Imitation Loss for Neural Text Generation
Scheduled sampling is a curriculum learning strategy that gradually exposes the model to its own predictions during training to mitigate this bias.
SPT: Semi-Parametric Prompt Tuning for Multitask Prompted Learning
Pre-trained large language models can efficiently interpolate human-written prompts in a natural way.
Is GPT-3 a Good Data Annotator?
In this paper, we evaluate the performance of GPT-3 as a data annotator by comparing it with traditional data annotation methods and analyzing its output on a range of tasks.
Evaluating Psychological Safety of Large Language Models
Despite being instruction fine-tuned with safety metrics to reduce toxicity, InstructGPT, GPT-3. 5, and GPT-4 still showed dark personality patterns; these models scored higher than self-supervised GPT-3 on the Machiavellianism and narcissism traits on SD-3.
Unsupervised Summarization Re-ranking
With the rise of task-specific pre-training objectives, abstractive summarization models like PEGASUS offer appealing zero-shot performance on downstream summarization tasks.
Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation
Human evaluation is the foundation upon which the evaluation of both summarization systems and automatic metrics rests.
Learning Label Modular Prompts for Text Classification in the Wild
Machine learning models usually assume i. i. d data during training and testing, but data and tasks in real world often change over time.
BotSIM: An End-to-End Bot Simulation Toolkit for Commercial Task-Oriented Dialog Systems
BotSIM adopts a layered design comprising the infrastructure layer, the adaptor layer and the application layer.
BotSIM: An End-to-End Bot Simulation Framework for Commercial Task-Oriented Dialog Systems
We have open-sourced the toolkit at https://github. com/salesforce/botsim
Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations
Due to the huge amount of parameters, fine-tuning of pretrained language models (PLMs) is prone to overfitting in the low resource scenarios.
Alleviating Sparsity of Open Knowledge Graphs with Ternary Contrastive Learning
Sparsity of formal knowledge and roughness of non-ontological construction make sparsity problem particularly prominent in Open Knowledge Graphs (OpenKGs).
Towards Summary Candidates Fusion
To bypass this limitation, we propose a new paradigm in second-stage abstractive summarization called SummaFusion that fuses several summary candidates to produce a novel abstractive second-stage summary.
OpenCQA: Open-ended Question Answering with Charts
In the first setting, a chart and the accompanying article is provided as input to the model.
Improving Conversational Recommender System via Contextual and Time-Aware Modeling with Less Domain-Specific Knowledge
In addition to conducting experiments on a popular dataset (ReDial), we also include a multi-domain dataset (OpenDialKG) to show the effectiveness of our model.
CoHS-CQG: Context and History Selection for Conversational Question Generation
While previous studies mainly focus on how to model the flow and alignment of the conversation, there has been no thorough study to date on which parts of the context and history are necessary for the model.
FOLIO: Natural Language Reasoning with First-Order Logic
We present FOLIO, a human-annotated, logically complex and diverse dataset for reasoning in natural language (NL), equipped with first-order logic (FOL) annotations.
Refining Low-Resource Unsupervised Translation by Language Disentanglement of Multilingual Model
Numerous recent work on unsupervised machine translation (UMT) implies that competent unsupervised translations of low-resource and unrelated languages, such as Nepali or Sinhala, are only possible if the model is trained in a massive multilingual environment, where these low-resource languages are mixed with high-resource counterparts.
Data Selection Curriculum for Neural Machine Translation
In this work, we introduce a two-stage curriculum training framework for NMT where we fine-tune a base NMT model on subsets of data, selected by both deterministic scoring using pre-trained methods and online scoring that considers prediction scores of the emerging NMT model.
ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning
To address the unique challenges in our benchmark involving visual and logical reasoning over charts, we present two transformer-based models that combine visual features and the data table of the chart in a unified way to answer questions.
Ranked #1 on
Chart Question Answering
on RealCQA
SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization
Sequence-to-sequence neural networks have recently achieved great success in abstractive summarization, especially through fine-tuning large pre-trained language models on the downstream dataset.
Ranked #2 on
Document Summarization
on CNN / Daily Mail
Chart-to-Text: A Large-Scale Benchmark for Chart Summarization
We also introduce a number of state-of-the-art neural models as baselines that utilize image captioning and data-to-text generation techniques to tackle two problem variations: one assumes the underlying data table of the chart is available while the other needs to extract data from chart images.
Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation
Existing continual relation learning (CRL) methods rely on plenty of labeled training data for learning a new task, which can be hard to acquire in real scenario as getting large and representative labeled data is often expensive and time-consuming.
Enhancing Multilingual Language Model with Massive Multilingual Knowledge Triples
In this work, we explore methods to make better use of the multilingual annotation and language agnostic property of KG triples, and present novel knowledge based multilingual language models (KMLMs) trained directly on the knowledge triples.
A Unified Speaker Adaptation Approach for ASR
For model adaptation, we use a novel gradual pruning method to adapt to target speakers without changing the model architecture, which to the best of our knowledge, has never been explored in ASR.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Cascaded Fast and Slow Models for Efficient Semantic Code Search
The goal of natural language semantic code search is to retrieve a semantically relevant code snippet from a fixed set of candidates using a natural language query.
Rethinking Self-Supervision Objectives for Generalizable Coherence Modeling
Given the claims of improved text generation quality across various pre-trained neural models, we consider the coherence evaluation of machine generated text to be one of the principal applications of coherence models that needs to be investigated.
GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems
Much recent progress in task-oriented dialogue (ToD) systems has been driven by available annotation data across multiple domains for training.
LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5
Existing approaches to lifelong language learning rely on plenty of labeled data for learning a new task, which is hard to obtain in most real scenarios.
Contrastive Clustering to Mine Pseudo Parallel Data for Unsupervised Translation
Modern unsupervised machine translation systems mostly train their models by generating synthetic parallel training data from large unlabeled monolingual corpora of different languages through various means, such as iterative back-translation.
CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation
We present CodeT5, a unified pre-trained encoder-decoder Transformer model that better leverages the code semantics conveyed from the developer-assigned identifiers.
Ranked #1 on
Text-to-Code Generation
on CodeXGLUE - CONCODE
MulDA: A Multilingual Data Augmentation Framework for Low-Resource Cross-Lingual NER
With the source-language data as well as the translated data, a generation-based multilingual data augmentation method is introduced to further increase diversity by generating synthetic labeled data in multiple languages.
Remember What You have drawn: Semantic Image Manipulation with Memory
Therefore, in this paper, we propose a memory-based Image Manipulation Network (MIM-Net), where a set of memories learned from images is introduced to synthesize the texture information with the guidance of the textual description.
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
Most existing methods employ a transformer-based multimodal encoder to jointly model visual tokens (region-based image features) and word tokens.
Ranked #5 on
Open Vocabulary Attribute Detection
on OVAD-Box benchmark
(using extra training data)
A Conditional Splitting Framework for Efficient Constituency Parsing
We introduce a generic seq2seq parsing framework that casts constituency parsing problems (syntactic and discourse parsing) into a series of conditional splitting decisions.
Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation
Advanced large-scale neural language models have led to significant success in many language generation tasks.
AUGVIC: Exploiting BiText Vicinity for Low-Resource NMT
We show that AUGVIC helps to attenuate the discrepancies between relevant and distant-domain monolingual data in traditional back-translation.
RST Parsing from Scratch
We introduce a novel top-down end-to-end formulation of document-level discourse parsing in the Rhetorical Structure Theory (RST) framework.
Ranked #16 on
Discourse Parsing
on RST-DT
Reliability Testing for Natural Language Processing Systems
Questions of fairness, robustness, and transparency are paramount to address before deploying NLP systems.
Addressing the Vulnerability of NMT in Input Perturbations
Neural Machine Translation (NMT) has achieved significant breakthrough in performance but is known to suffer vulnerability to input perturbations.
Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots
Multilingual models have demonstrated impressive cross-lingual transfer performance.
Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings
We operationalize our framework by first proposing a novel sense-aware cross entropy loss to model word senses explicitly.
Weakly Supervised Neuro-Symbolic Module Networks for Numerical Reasoning
Neural Module Networks (NMNs) have been quite successful in incorporating explicit reasoning as learnable modules in various question answering tasks, including the most generic form of numerical reasoning over text in Machine Reading Comprehension (MRC).
XLA: A Robust Unsupervised Data Augmentation Framework for Cross-Lingual NLP
Transfer learning has yielded state-of-the-art (SoTA) results in many supervised NLP tasks.
DiP Benchmark Tests: Evaluation Benchmarks for Discourse Phenomena in MT
Despite increasing instances of machine translation (MT) systems including extrasentential context information, the evidence for translation quality improvement is sparse, especially for discourse phenomena.
Self-Supervised Relationship Probing
Structured representations of images that model visual relationships are beneficial for many vision and vision-language applications.
DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks
Data augmentation techniques have been widely used to improve machine learning performance as they enhance the generalization capability of models.
Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data Augmentation
Models pretrained with self-supervised objectives on large text corpora achieve state-of-the-art performance on English text summarization tasks.
Online Conversation Disentanglement with Pointer Networks
We also introduce a joint-learning objective to better capture contextual information.
Pronoun-Targeted Fine-tuning for NMT with Hybrid Losses
Our sentence-level model shows a 0. 5 BLEU improvement on both the WMT14 and the IWSLT13 De-En testsets, while our contextual model achieves the best results, improving from 31. 81 to 32 BLEU on WMT14 De-En testset, and from 32. 10 to 33. 13 on the IWSLT13 De-En testset, with corresponding improvements in pronoun translation.
Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading
Based on the learned EDU and entailment representations, we either reply to the user our final decision "yes/no/irrelevant" of the initial question, or generate a follow-up question to inquiry more information.
UNISON: Unpaired Cross-lingual Image Captioning
In this work, we present a novel unpaired cross-lingual method to generate image captions without relying on any caption corpus in the source or the target language.
Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change Captioning
In this paper, we propose a novel visual encoder to explicitly distinguish viewpoint changes from semantic changes in the change captioning task.
GeDi: Generative Discriminator Guided Sequence Generation
While large-scale language models (LMs) are able to imitate the distribution of natural language well enough to generate realistic text, it is difficult to control which regions of the distribution they generate.
Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading
The goal of conversational machine reading is to answer user questions given a knowledge base text which may require asking clarification questions.
Efficient Constituency Parsing by Pointing
We propose a novel constituency parsing model that casts the parsing problem into a series of pointing tasks.
Differentiable Window for Dynamic Local Attention
We propose Differentiable Window, a new neural module and general purpose component for dynamic window selection.
Cross-model Back-translated Distillation for Unsupervised Machine Translation
Recent unsupervised machine translation (UMT) systems usually employ three main principles: initialization, language modeling and iterative back-translation, though they may apply them differently.
Unsupervised Word Translation with Adversarial Autoencoder
Crosslingual word embeddings learned from monolingual embeddings have a crucial role in many downstream tasks, ranging from machine translation to transfer learning.
EMT: Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading
The goal of conversational machine reading is to answer user questions given a knowledge base text which may require asking clarification questions.
It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations
Training on only perfect Standard English corpora predisposes pre-trained neural networks to discriminate against minorities from non-standard linguistic backgrounds (e. g., African American Vernacular English, Colloquial Singapore English, etc.).
Can Your Context-Aware MT System Pass the DiP Benchmark Tests? : Evaluation Benchmarks for Discourse Phenomena in Machine Translation
Despite increasing instances of machine translation (MT) systems including contextual information, the evidence for translation quality improvement is sparse, especially for discourse phenomena.
Rethinking Coherence Modeling: Synthetic vs. Downstream Tasks
Although coherence modeling has come a long way in developing novel models, their evaluation on downstream applications for which they are purportedly developed has largely been neglected.
Mind Your Inflections! Improving NLP for Non-Standard Englishes with Base-Inflection Encoding
Inflectional variation is a common feature of World Englishes such as Colloquial Singapore English and African American Vernacular English.
LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent Space
Most of the successful and predominant methods for bilingual lexicon induction (BLI) are mapping-based, where a linear mapping function is learned with the assumption that the word embedding spaces of different languages exhibit similar geometric structures (i. e., approximately isomorphic).
Bilingual Lexicon Induction
Cross-Lingual Word Embeddings
+1
VD-BERT: A Unified Vision and Dialog Transformer with BERT
By contrast, in this work, we propose VD-BERT, a simple yet effective framework of unified vision-dialog Transformer that leverages the pretrained BERT language models for Visual Dialog tasks.
UXLA: A Robust Unsupervised Data Augmentation Framework for Zero-Resource Cross-Lingual NLP
We propose UXLA, a novel unsupervised data augmentation framework for zero-resource transfer learning scenarios.
Tree-structured Attention with Hierarchical Accumulation
Incorporating hierarchical structures like constituency trees has been shown to be effective for various natural language processing (NLP) tasks.
Pairwise Neural Machine Translation Evaluation
We present a novel framework for machine translation evaluation using neural networks in a pairwise setting, where the goal is to select the better translation from a pair of hypotheses, given the reference translation.
DiscoTK: Using Discourse Structure for Machine Translation Evaluation
We present novel automatic metrics for machine translation evaluation that use discourse structure and convolution kernels to compare the discourse tree of an automatic translation with that of the human reference.
Zero-Resource Cross-Lingual Named Entity Recognition
Recently, neural methods have achieved state-of-the-art (SOTA) results in Named Entity Recognition (NER) tasks for many languages without the need for manually crafted features.
Global Thread-Level Inference for Comment Classification in Community Question Answering
Community question answering, a recent evolution of question answering in the Web context, allows a user to quickly consult the opinion of a number of people on a particular topic, thus taking advantage of the wisdom of the crowd.
Resurrecting Submodularity for Neural Text Generation
The resulting attention module offers an architecturally simple and empirically effective method to improve the coverage of neural text generation.
Data Diversification: A Simple Strategy For Neural Machine Translation
Our method achieves state-of-the-art BLEU scores of 30. 7 and 43. 7 in the WMT'14 English-German and English-French translation tasks, respectively.
Ranked #9 on
Machine Translation
on WMT2014 English-German
Enhancing Attention with Explicit Phrasal Alignments
The attention mechanism is an indispensable component of any state-of-the-art neural machine translation system.
Using Clinical Notes with Time Series Data for ICU Management
Monitoring patients in ICU is a challenging and high-cost task.
A Unified Neural Coherence Model
In this paper, we propose a unified coherence model that incorporates sentence grammar, inter-sentence coherence relations, and global coherence patterns into a common neural framework.
Evaluating Pronominal Anaphora in Machine Translation: An Evaluation Measure and a Test Suite
The ongoing neural revolution in machine translation has made it easier to model larger contexts beyond the sentence-level, which can potentially help resolve some discourse-level ambiguities such as pronominal anaphora, thus enabling better translations.
Hierarchical Pointer Net Parsing
Transition-based top-down parsing with pointer networks has achieved state-of-the-art results in multiple parsing tasks, while having a linear time complexity.
Watch It Twice: Video Captioning with a Refocused Video Encoder
With the rapid growth of video data and the increasing demands of various applications such as intelligent video search and assistance toward visually-impaired people, video captioning task has received a lot of attention recently in computer vision and natural language processing fields.
Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks
Claim verification is generally a task of verifying the veracity of a given claim, which is critical to many downstream applications.
Discourse Analysis and Its Applications
Discourse processing is a suite of Natural Language Processing (NLP) tasks to uncover linguistic structures from texts at several levels, which can support many downstream applications.
A Unified Linear-Time Framework for Sentence-Level Discourse Parsing
We propose an efficient neural framework for sentence-level discourse analysis in accordance with Rhetorical Structure Theory (RST).
Revisiting Adversarial Autoencoder for Unsupervised Word Translation with Cycle Consistency and Improved Training
Adversarial training has shown impressive success in learning bilingual dictionary without any parallel data by mapping monolingual embeddings to a shared space.
Adaptation of Hierarchical Structured Models for Speech Act Recognition in Asynchronous Conversation
We address the problem of speech act recognition (SAR) in asynchronous conversations (forums, emails).
Unpaired Image Captioning via Scene Graph Alignments
Most of current image captioning models heavily rely on paired image-caption datasets.
Modeling Speech Acts in Asynchronous Conversations: A Neural-CRF Approach
Participants in an asynchronous conversation (e. g., forum, e-mail) interact with each other at different times, performing certain communicative acts, called speech acts (e. g., question, request).
Adversarial Unsupervised Representation Learning for Activity Time-Series
Sufficient physical activity and restful sleep play a major role in the prevention and cure of many chronic conditions.
Reuse and Adaptation for Entity Resolution through Transfer Learning
Entity resolution (ER) is one of the fundamental problems in data integration, where machine learning (ML) based classifiers often provide the state-of-the-art results.
Joint Multitask Learning for Community Question Answering Using Task-Specific Embeddings
We address jointly two important tasks for Question Answering in community forums: given a new question, (i) find related existing questions, and (ii) find relevant answers to this new question.
Video Captioning with Boundary-aware Hierarchical Language Decoding and Joint Video Prediction
In this paper, we propose a boundary-aware hierarchical language decoder for video captioning, which consists of a high-level GRU based language decoder, working as a global (caption-level) language model, and a low-level GRU based language decoder, working as a local (phrase-level) language model.
Domain Adaptation with Adversarial Training and Graph Embeddings
In such scenarios, a DNN model can leverage labeled and unlabeled data from a related domain, but it has to deal with the shift in data distributions between the source and the target domains.
Coherence Modeling of Asynchronous Conversations: A Neural Entity Grid Approach
We propose a novel coherence model for written asynchronous conversations (e. g., forums, emails), and show its applications in coherence assessment and thread reconstruction tasks.
Graph Based Semi-supervised Learning with Convolution Neural Networks to Classify Crisis Related Tweets
During time-critical situations such as natural disasters, rapid classification of data posted on social networks by affected people is useful for humanitarian organizations to gain situational awareness and to plan response efforts.
Models for Capturing Temporal Smoothness in Evolving Networks for Learning Latent Representation of Nodes
However, existing models for learning latent representation are inadequate for obtaining the representation vectors of the vertices for different time-stamps of a dynamic network in a meaningful way.
VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions
Most existing works in visual question answering (VQA) are dedicated to improving the accuracy of predicted answers, while disregarding the explanations.
Ranked #4 on
Explanatory Visual Question Answering
on GQA-REX
Explanatory Visual Question Answering
Multi-Task Learning
+1
Unpaired Image Captioning by Language Pivoting
Image captioning is a multimodal task involving computer vision and natural language processing, where the goal is to learn a mapping from the image to its natural language description.
Hyperedge2vec: Distributed Representations for Hyperedges
We present a number of interesting baselines, some of which adapt existing node-level embedding models to the hyperedge-level, as well as sequence based language techniques which are adapted for set structured hypergraph topology.
Co-Morbidity Exploration on Wearables Activity Data Using Unsupervised Pre-training and Multi-Task Learning
This is a critical barrier for the use of this new source of signal for healthcare decision making.
Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models
Textual-visual cross-modal retrieval has been a hot research topic in both computer vision and natural language processing communities.
Discourse Structure in Machine Translation Evaluation
In this article, we explore the potential of using sentence-level discourse structure for machine translation evaluation.