Search Results for author:
Found 43 papers, 25 papers with code
A Cognitive Evaluation Benchmark of Image Reasoning and Description for Large Vision-Language Models
Large Vision-Language Models (LVLMs), despite their recent success, are hardly comprehensively tested for their cognitive abilities.
Phonetic and Lexical Discovery of a Canine Language using HuBERT
This paper delves into the pioneering exploration of potential communication patterns within dog vocalizations and transcends traditional linguistic analysis barriers, which heavily relies on human priori knowledge on limited datasets to find sound units in dog vocalization.
On the Efficacy of Eviction Policy for Key-Value Constrained Generative Language Model Inference
Despite the recent success associated with Large Language Models (LLMs), they are notably cost-prohibitive to deploy in resource-constrained environments due to their excessive memory and computational demands.
PsyEval: A Suite of Mental Health Related Tasks for Evaluating Large Language Models
This comprehensive framework is designed to thoroughly assess the unique challenges and intricacies of mental health-related tasks, making PsyEval a highly specialized and valuable tool for evaluating LLM performance in this domain.
Zero-shot Faithfulness Evaluation for Text Summarization with Foundation Language Model
Despite tremendous improvements in natural language generation, summarization models still suffer from the unfaithfulness issue.
Context Compression for Auto-regressive Transformers with Sentinel Tokens
The quadratic complexity of the attention module makes it gradually become the bulk of compute in Transformer-based LLMs during generation.
EMO: Earth Mover Distance Optimization for Auto-Regressive Language Modeling
In this paper, we propose Earth Mover Distance Optimization (EMO) for auto-regressive language modeling.
Low-Rank Prune-And-Factorize for Language Model Compression
The components underpinning PLMs -- large weight matrices -- were shown to bear considerable redundancy.
Reducing Sensitivity on Speaker Names for Text Generation from Dialogues
Changing speaker names consistently throughout a dialogue should not affect its meaning and corresponding outputs for text generation from dialogues.
LLM-empowered Chatbots for Psychiatrist and Patient Simulation: Application and Evaluation
Empowering chatbots in the field of mental health is receiving increasing amount of attention, while there still lacks exploration in developing and evaluating chatbots in psychiatric outpatient scenarios.
Pruning Pre-trained Language Models with Principled Importance and Self-regularization
Iterative pruning is one of the most effective compression methods for pre-trained language models.
Semantic Space Grounded Weighted Decoding for Multi-Attribute Controllable Dialogue Generation
Controlling chatbot utterance generation with multiple attributes such as personalities, emotions and dialogue acts is a practically useful but under-studied problem.
In-sample Curriculum Learning by Sequence Completion for Natural Language Generation
Curriculum learning has shown promising improvements in multiple domains by training machine learning models from easy samples to hard ones.
Taxonomy of Abstractive Dialogue Summarization: Scenarios, Approaches and Future Directions
Abstractive dialogue summarization is to generate a concise and fluent summary covering the salient information in a dialogue among two or more interlocutors.
Symptom Identification for Interpretable Detection of Multiple Mental Disorders
Mental disease detection (MDD) from social media has suffered from poor generalizability and interpretability, due to lack of symptom modeling.
Few-Shot Natural Language Inference Generation with PDD: Prompt and Dynamic Demonstration
Natural Language Inference Generation task is to generate a text hypothesis given a text premise and a logical relation between the two.
Psychiatric Scale Guided Risky Post Screening for Early Detection of Depression
Depression is a prominent health challenge to the world, and early risk detection (ERD) of depression from online posts can be a promising technique for combating the threat.
Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation
News recommendation for anonymous readers is a useful but challenging task for many news portals, where interactions between readers and articles are limited within a temporary login session.
Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval
Current text-image approaches (e. g., CLIP) typically adopt dual-encoder architecture us- ing pre-trained vision-language representation.
Post-Training Dialogue Summarization using Pseudo-Paraphrasing
Previous dialogue summarization techniques adapt large language models pretrained on the narrative text by injecting dialogue-specific features into the models.
Modeling Multi-level Context for Informational Bias Detection by Contrastive Learning and Sentential Graph Network
Informational bias is widely present in news articles.
Can Audio Captions Be Evaluated with Image Caption Metrics?
Current metrics are found in poor correlation with human annotations on these datasets.
Diverse and Specific Clarification Question Generation with Keywords
Due to the variety of possible user backgrounds and use cases, the information need can be quite diverse but also specific to a detailed topic, while previous works assume generating one CQ per context and the results tend to be generic.
Statistically Profiling Biases in Natural Language Reasoning Datasets and Models
Recent work has indicated that many natural language understanding and reasoning datasets contain statistical cues that may be taken advantaged of by NLP models whose capability may thus be grossly overestimated.
DDRel: A New Dataset for Interpersonal Relation Classification in Dyadic Dialogues
In this paper, we propose the task of relation classification of interlocutors based on their dialogues.
Ranked #1 on
Dialog Relation Extraction
on DDRel
Multi-turn Response Selection using Dialogue Dependency Relations
In this paper, we propose a dialogue extraction algorithm to transform a dialogue history into threads based on their dependency relations.
Matching Questions and Answers in Dialogues from Online Forums
Matching question-answer relations between two turns in conversations is not only the first step in analyzing dialogue structures, but also valuable for training dialogue systems.
MICK: A Meta-Learning Framework for Few-shot Relation Classification with Small Training Data
In this framework, models not only strive to classify query instances, but also seek underlying knowledge about the support instances to obtain better instance representations.
ST$^2$: Small-data Text Style Transfer via Multi-task Meta-Learning
Text style transfer aims to paraphrase a sentence in one style into another style while preserving content.
Knowledge-Driven Distractor Generation for Cloze-style Multiple Choice Questions
In this paper, we propose a novel configurable framework to automatically generate distractive choices for open-domain cloze-style multiple-choice questions, which incorporates a general-purpose knowledge base to effectively create a small distractor candidate set, and a feature-rich learning-to-rank model to select distractors that are both plausible and reliable.
Unpack Local Model Interpretation for GBDT
Besides the commonly used feature importance as a global interpretation, feature contribution is a local measure that reveals the relationship between a specific instance and the related output.
AliCoCo: Alibaba E-commerce Cognitive Concept Net
However, user needs in e-commerce are still not well defined, and none of the existing ontologies has the enough depth and breadth for universal user needs understanding.
Adapted tree boosting for Transfer Learning
Secure online transaction is an essential task for e-commerce platforms.
Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations
Previous work on cross-lingual sequence labeling tasks either requires parallel data or bridges the two languages through word-byword matching.
Conceptualize and Infer User Needs in E-commerce
Understanding latent user needs beneath shopping behaviors is critical to e-commercial applications.
Exact-K Recommendation via Maximal Clique Optimization
This paper targets to a novel but practical recommendation problem named exact-K recommendation.
Automatic Generation of Text Descriptive Comments for Code Blocks
We propose a framework to automatically generate descriptive comments for source code blocks.
Deep Cascade Multi-task Learning for Slot Filling in Online Shopping Assistant
Slot filling is a critical task in natural language understanding (NLU) for dialog systems.
Automatic Generation of Chinese Short Product Titles for Mobile Display
This paper studies the problem of automatically extracting a short title from a manually written longer description of E-commerce products for display on mobile devices.
Representing Verbs as Argument Concepts
Verbs play an important role in the understanding of natural language text.
Automatic Extraction of Commonsense LocatedNear Knowledge
LocatedNear relation is a kind of commonsense knowledge describing two physical objects that are typically found near each other in real life.
Improving Attention Modeling with Implicit Distortion and Fertility for Machine Translation
In neural machine translation, the attention mechanism facilitates the translation process by producing a soft alignment between the source sentence and the target sentence.
Data-Driven Metaphor Recognition and Explanation
Recognizing metaphors and identifying the source-target mappings is an important task as metaphorical text poses a big challenge for machine reading.
