Papers by Junwei Bao

19 papers
Composable Text Controls in Latent Space with ODEs (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to composable text operations often require plug-and-play . a single LM can perform arbitrary text operation composition in the latent space .
Approach: They propose an efficient approach for composable text operations in the latent space of text . they connect pretrained LMs to the laten space and adapt them to the space .
Outcome: The proposed approach improves on existing methods in the latent space of text.
SGG: Learning to Select, Guide, and Generate for Keyphrase Generation (2021.naacl-main)

Copied to clipboard

Challenge: Existing keyphrase generation approaches synchronously generate present and absent keyphrases without explicitly distinguishing these two categories.
Approach: They propose to deal with present and absent keyphrases separately with different mechanisms by using a hierarchical neural network with a pointing-based selector and a selection-guided generator.
Outcome: The proposed model outperforms baselines on four keyphrase generation tasks and shows extensibility in natural language generation tasks.
UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods for question answering using knowledge resources are mixed-of-experts and semantic parsing-based.
Approach: They propose a semantic-parsing-based approach to perform Unified discrete Reasoning over heterogeneous knowledge resources as Program Generation.
Outcome: The proposed approach improves interpretability and scalability over table and text . it achieves promising performance on the TAT-QA dataset without annotation .
AUGUST: an Automatic Generation Understudy for Synthesizing Conversational Recommendation Datasets (2023.findings-acl)

Copied to clipboard

Challenge: Existing work on conversational recommendation systems lacks high-quality data . existing datasets lack large-scale and high-level data based on human annotators .
Approach: They propose an automatic dataset synthesis approach that generates large-scale recommendation dialogues using structured graphs based on user-item information from the real world.
Outcome: The proposed approach can generate large-scale and high-quality recommendation dialogues . it exploits user preferences, knowledge graphs, and conversation ability from existing datasets based on real-world data .
Mars: Modeling Context & State Representations with Contrastive Learning for End-to-End Task-Oriented Dialog (2023.findings-acl)

Copied to clipboard

Challenge: Empirical results show dialog context representations are more conducive to multi-turn task-oriented dialog.
Approach: They propose an end-to-end task-oriented dialog system with two contrastive learning strategies to model relationship between dialog context and belief/action state representations.
Outcome: Empirical results show that dialog context representations are more conducive to multi-turn task-oriented dialog.
Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT (2022.acl-long)

Copied to clipboard

Challenge: Transformer-based pre-trained models achieve state-of-the-art results, but they can be prohibitively costly.
Approach: They propose a fine- and coarse-granularity hybrid self-attention that shortens the computational sequence length in self- attention by progressively shortening the computational time.
Outcome: The proposed model reduces computation cost by shortening the computational sequence length in self-attention.
Learning to Decouple Relations: Few-Shot Relation Classification with Entity-Guided Attention and Confusion-Aware Training (2020.coling-main)

Copied to clipboard

Challenge: Existing few-shot relation classifiers struggle to distinguish them with few annotated instances due to high co-occurrence of some relations .
Approach: They propose a few-shot relation classification model with two mechanisms to decouple easily-confused relations.
Outcome: The proposed model achieves comparable and even better results to strong baselines in terms of accuracy.
BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialog (2022.findings-naacl)

Copied to clipboard

Challenge: Existing task-oriented dialog systems suffer from error propagation from inaccurate dialog states and responses.
Approach: They propose a back reconstruction approach for end-to-end task-oriented dialog system . they use back reconstruction to reconstruct the original input context from the generated dialog states .
Outcome: Extensive experiments on MultiWOZ 2.0 and CamRest676 show the effectiveness of the proposed model.
MuGER2: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answering (2022.findings-emnlp)

Copied to clipboard

Challenge: Conventional HQA models retrieve coarse- or fine-grained evidence to reason the answer . however, they neglect a more general scenario requiring reasoning over heterogeneous data to answer a question.
Approach: They propose a multi-granularity evidence retrieval and reasoning approach to answer questions over heterogeneous data using tables and passages linked to table cells.
Outcome: The proposed approach significantly boosts the performance on the HybridQA dataset.
Don’t Take It Literally: An Edit-Invariant Sequence Loss for Text Generation (2022.naacl-main)

Copied to clipboard

Challenge: Neural text generation models are typically trained by maximizing log-likelihood with the sequence cross entropy (CE) loss.
Approach: They propose an Edit-Invariant Sequence Loss method which computes the matching loss of a target sequence with all n-grams in the generated sequence.
Outcome: The proposed method outperforms the common CE loss and strong baselines on a wide range of tasks.
MoNET: Tackle State Momentum via Noise-Enhanced Training for Dialogue State Tracking (2023.findings-acl)

Copied to clipboard

Challenge: Experimental results show that MoNET outperforms previous DST methods in alleviating state momentum issues and improving the anti-noise ability.
Approach: They propose to use previous state of each turn in training data as input to learn to predict current state.
Outcome: The proposed model outperforms existing methods on multiWOZ datasets and shows that it can update and correct slot values and improve anti-noise ability.
Comet: Dialog Context Fusion Mechanism for End-to-End Task-Oriented Dialog with Multi-task Learning (2025.coling-main)

Copied to clipboard

Challenge: Existing end-to-end task-oriented dialog systems often encounter challenges arising from implicit information, coreference, and the presence of noisy and irrelevant data within the dialog context.
Approach: They propose a dialog context fusion mechanism for end-to-end task-oriented dialog augmented with three additional tasks: dialog summarization, domain prediction, and slot detection.
Outcome: The proposed method achieves state-of-the-art on the MultiWOZ and CrossWOZ datasets.
RoR: Read-over-Read for Long Document Machine Reading Comprehension (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing models for machine reading comprehension are limited to individual chunks due to encoding length constraint.
Approach: They propose a read-over-read method that expands the reading field from chunk to document by predicting regional answers for each chunk.
Outcome: Extensive experiments on QuAC and TriviaQA show that the proposed model performs well for long document reading.
OPERA: Operation-Pivoted Discrete Reasoning over Text (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods to predict logical forms ignore the utilization of symbolic operations and lack reasoning ability and interpretability.
Approach: They propose an operation-pivoted discrete reasoning framework that uses symbolic operations as neural modules to facilitate reasoning ability and interpretability.
Outcome: Extensive experiments on DROP and RACENum datasets show the reasoning ability of OPERA.
Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Knowledge base question answering (KBQA) is a challenging task, particularly in parsing intricate questions into executable logical forms.
Approach: They propose a framework to generate logical forms through direct interaction with knowledge bases (KBs) by annotating a dataset with step-wise reasoning processes.
Outcome: The proposed framework achieves competitive results on the WebQuestionsSP, ComplexWebQuestIONS, KQA Pro, and MetaQA datasets with a minimal number of examples (shots). Importantly, the proposed model supports manual intervention, allowing for the iterative refinement of LLM outputs.
P3LM: Probabilistically Permuted Prophet Language Modeling for Generative Pre-Training (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing autoregressive left-to-right (L2R) models are limited to unidirectional information and constrained on strong local dependencies.
Approach: They propose a probabilistically permuted prophet language model which strengthens the modeling of bidirectional information and long token dependencies for sequence generation.
Outcome: Experiments on GLGE dataset show that P3LM improves on natural language generation tasks.
LUNA: Learning Slot-Turn Alignment for Dialogue State Tracking (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods exploit the utterances of all dialogue turns to assign value to slots . this can lead to suboptimal results due to information introduced from irrelevant utterrances .
Approach: They propose a SLot-TUrN Alignment enhanced approach to assign slot value . they explicitly align each slot with its most relevant utterance and then predict the corresponding value based on this aligned utteration.
Outcome: The proposed approach achieves state-of-the-art on three multi-domain task-oriented dialogue datasets.
CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Tracking (2022.aacl-short)

Copied to clipboard

Challenge: Existing few-shot dialogue state tracking (DST) methods transfer knowledge from labeled data into DST, but collecting large amount of labeles is laborious.
Approach: They propose a few-shot dialogue state tracking framework that integrates self-training and self-supervised learning methods into the framework.
Outcome: The proposed framework achieves competitive performance in several few-shot scenarios.
RevCore: Review-Augmented Conversational Recommendation (2021.findings-acl)

Copied to clipboard

Challenge: Existing conversational recommendation systems lack item information when conducted on short dialogue history and unfamiliar items.
Approach: They propose a framework where reviews are seamlessly incorporated into conversational recommendation systems.
Outcome: The proposed framework yields better performance on recommendation and conversation responding.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations