Search Results for author:
Found 14 papers, 4 papers with code
CQG: A Simple and Effective Controlled Generation Framework for Multi-hop Question Generation
CQG employs a simple method to generate the multi-hop questions that contain key entities in multi-hop reasoning chains, which ensure the complexity and quality of the questions.
Question Calibration and Multi-Hop Modeling for Temporal Question Answering
In the real world, many facts contained in KGs are time-constrained thus temporal KGQA has received increasing attention.
Anything in Any Scene: Photorealistic Video Object Insertion
Our proposed general framework encompasses three key processes: 1) integrating a realistic object into a given scene video with proper placement to ensure geometric realism; 2) estimating the sky and environmental lighting distribution and simulating realistic shadows to enhance the light realism; 3) employing a style transfer network that refines the final video output to maximize photorealism.
Frame-wise streaming end-to-end speaker diarization with non-autoregressive self-attention-based attractors
This work proposes a frame-wise online/streaming end-to-end neural diarization (FS-EEND) method in a frame-in-frame-out fashion.
Unleashing Potential of Evidence in Knowledge-Intensive Dialogue Generation
To fully Unleash the potential of evidence, we propose a framework to effectively incorporate Evidence in knowledge-Intensive Dialogue Generation (u-EIDG).
High-Speed and Energy-Efficient Non-Volatile Silicon Photonic Memory Based on Heterogeneously Integrated Memresonator
Recently, interest in programmable photonics integrated circuits has grown as a potential hardware framework for deep neural networks, quantum computing, and field programmable arrays (FPGAs).
Time-aware Multiway Adaptive Fusion Network for Temporal Knowledge Graph Question Answering
For each given question, TMA first extracts the relevant concepts from the KG, and then feeds them into a multiway adaptive module to produce a \emph{temporal-specific} representation of the question.
Dual Path Modeling for Semantic Matching by Perceiving Subtle Conflicts
To alleviate this problem, we propose a novel Dual Path Modeling Framework to enhance the model's ability to perceive subtle differences in sentence pairs by separately modeling affinity and difference semantics.
Robust Lottery Tickets for Pre-trained Language Models
Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching accuracy comparable to the original models.
Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion
Transformer-based pre-trained models like BERT have achieved great progress on Semantic Sentence Matching.
DABERT: Dual Attention Enhanced BERT for Semantic Matching
To alleviate this problem, we propose a novel Dual Attention Enhanced BERT (DABERT) to enhance the ability of BERT to capture fine-grained differences in sentence pairs.
Searching for Optimal Subword Tokenization in Cross-domain NER
Input distribution shift is one of the vital problems in unsupervised domain adaptation (UDA).
Asynchronous Deep Interaction Network for Natural Language Inference
However, in the process of reasoning, the role of the two sentences is obviously different, and the sentence pairs for NLI are asymmetrical corpora.
Transferring from Formal Newswire Domain with Hypernet for Twitter POS Tagging
However, from a linguistic perspective, Twitter users not only tend to mimic the formal expressions of traditional media, like news, but they also appear to be developing linguistically informal styles.
Ranked #2 on
Part-Of-Speech Tagging
on Ritter
