Search Results for author:
Found 18 papers, 9 papers with code
Towards Real-world Scenario: Imbalanced New Intent Discovery
New Intent Discovery (NID) aims at detecting known and previously undefined categories of user intent by utilizing limited labeled and massive unlabeled data.
RoNID: New Intent Discovery with Generated-Reliable Labels and Cluster-friendly Representations
To address the aforementioned challenges, we propose a Robust New Intent Discovery (RoNID) framework optimized by an EM-style method, which focuses on constructing reliable pseudo-labels and obtaining cluster-friendly discriminative representations.
m3P: Towards Multimodal Multilingual Translation with Multimodal Prompt
Our method aims to minimize the representation distance of different languages by regarding the image as a central language.
New Intent Discovery with Attracting and Dispersing Prototype
New Intent Discovery (NID) aims to recognize known and infer new intent categories with the help of limited labeled and large-scale unlabeled data.
xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning
To bridge the gap among different languages, we propose a cross-lingual instruction fine-tuning framework (xCOT) to transfer knowledge from high-resource languages to low-resource languages.
LogFormer: A Pre-train and Tuning Pipeline for Log Anomaly Detection
Log anomaly detection is a key component in the field of artificial intelligence for IT operations (AIOps).
MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL
Our framework comprises a core decomposer agent for Text-to-SQL generation with few-shot chain-of-thought reasoning, accompanied by two auxiliary agents that utilize external tools or models to acquire smaller sub-databases and refine erroneous SQL queries.
M2C: Towards Automatic Multimodal Manga Complement
In other words, the Multimodal Manga Complement (M2C) task has not been investigated, which aims to handle the aforementioned issues by providing a shared semantic space for vision and language understanding.
OWL: A Large Language Model for IT Operations
However, there is a lack of specialized LLMs for IT operations.
MT4CrossOIE: Multi-stage Tuning for Cross-lingual Open Information Extraction
Cross-lingual open information extraction aims to extract structured information from raw text across multiple languages.
KnowPrefix-Tuning: A Two-Stage Prefix-Tuning Framework for Knowledge-Grounded Dialogue Generation
We propose Knowledgeable Prefix Tuning (KnowPrefix-Tuning), a two-stage tuning framework, bypassing the retrieval process in a knowledge-grounded conversation system by injecting prior knowledge into the lightweight knowledge prefix.
GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking
However, the retrieved passages are not ideal for guiding answer generation because of the discrepancy between retrieval and generation, i. e., the candidate passages are all treated equally during the retrieval procedure without considering their potential to generate a proper answer.
Retrieval-Augmented Classification with Decoupled Representation
Retrieval augmented methods have shown promising results in various classification tasks.
Enhancing Dialogue Summarization with Topic-Aware Global- and Local- Level Centrality
The global one aims to identify vital sub-topics in the dialogue and the local one aims to select the most important context in each sub-topic.
Multilingual Entity and Relation Extraction from Unified to Language-specific Training
In this paper, we propose a two-stage multilingual training method and a joint model called Multilingual Entity and Relation Extraction framework (mERE) to mitigate language interference across languages.
TransLog: A Unified Transformer-based Framework for Log Anomaly Detection
Therefore, we propose a unified Transformer-based framework for log anomaly detection (\ourmethod{}), which is comprised of the pretraining and adapter-based tuning stage.
Jointly Learning to Repair Code and Generate Commit Message
We propose a novel task of jointly repairing program codes and generating commit messages.
StyleDGPT: Stylized Response Generation with Pre-trained Language Models
Generating responses following a desired style has great potentials to extend applications of open-domain dialogue systems, yet is refrained by lacking of parallel data for training.
