Natural language is an instrument of interaction, where interlocutors produce and comprehend language to relay information to accomplish their intents. Both opportunities and challenges arise from the interactive nature of language. The response of participants to the language they comprehend can form a strong learning signal: did I achieve my intent? In the first part, I will define a simple, and general framework to rapidly learn from interaction feedback, and show how to use this signal to learn to produce natural language instructions. I will then discuss the problem of language-conditioned reinforcement learning, where benchmark development has been hindered because computing rewards requires resolving language semantics. I will describe a new approach to address this challenge.

Natural Language Learning via Interaction

Emotion recognition is a crucial task for human conversation understanding. It becomes more challenging with the notion of multimodal data, e.g., language, voice, and facial expressions. As a typical solution, the global- and the local context information are exploited to predict the emotional label for every single sentence, i.e., utterance, in the dialogue. Specifically, the global representation could be captured via modeling of cross-modal interactions at the conversation level. The local one is often inferred using the temporal information of speakers or emotional shifts, which neglects vital factors at the utterance level. Additionally, most existing approaches take fused features of multiple modalities in an unified input without leveraging modality-specific representations. Motivating from these problems, we propose the Relational Temporal Graph Neural Network with Auxiliary Cross-Modality Interaction (CORECT), an novel neural network framework that effectively captures conversation-level cross-modality interactions and utterance-level temporal dependencies with the modality-specific manner for conversation understanding. Extensive experiments demonstrate the effectiveness of CORECT via its state-of-the-art results on the IEMOCAP and CMU-MOSEI datasets for the multimodal ERC task.

Conversation Understanding using Relational Temporal Graph Neural Networks with Auxiliary Cross-Modality Interaction | VIDEO

Sounding source localization is a challenging cross-modal task due to the difficulty of cross-modal alignment. 
Although supervised cross-modal methods achieve encouraging performance, heavy manual annotations are expensive and inefficient. Thus it is valuable and meaningful to develop unsupervised solutions. 
In this paper, we propose an **U**nsupervised **S**ounding **P**ixel **L**earning (USPL) approach which enables a pixel-level sounding source localization in unsupervised paradigm. 
We first design a mask augmentation based multi-instance contrastive learning to realize unsupervised cross-modal coarse localization, which aligns audio-visual features to obtain coarse sounding maps. 
Secondly, we present an *Unsupervised Sounding Map Refinement (SMR)* module which employs the visual semantic affinity learning to explore inter-pixel relations of adjacent coordinate features. It contributes to recovering the boundary of coarse sounding maps and obtaining fine sounding maps. 
Finally, a *Sounding Pixel Segmentation (SPS)* module is presented to realize audio-supervised semantic segmentation. 
Extensive experiments are performed on the AVSBench-S4 and VGGSound datasets, exhibiting encouraging results compared with previous SOTA methods.

Unsupervised Sounding Pixel Learning

Medical claim coding is the process of transforming medical records, usually presented as free texts written by clinicians, or discharge summaries, into structured codes in a classification system such as ICD-10 (International Classification of Diseases, Tenth Revision) or DRG (Diagnosis-Related Group) codes. This process is essential for medical billing and transitional care; however, manual coding is time-consuming, error-prone, and expensive. To solve these issues, we propose DRGCoder, an explainability-enhanced clinical claim coding system for the early prediction of medical severity DRGs (MS-DRGs), a classification system that categorizes patients' hospital stays into various DRG groups based on the severity of illness and mortality risk. The DRGCoder framework introduces a novel multi-task Transformer model for MS-DRG prediction, modeling both the DRG labels of the discharge summaries and the important, or salient words within he discharge summaries. We allow users to inspect DRGCoder's reasoning by visualizing the weights for each word of the input. Additionally, DRGCoder allows users to identify diseases within discharge summaries and compare across multiple discharge summaries. Our demo is available at https://huggingface.co/spaces/danielhajialigol/DRGCoder. A video demonstrating the demo can be found at https://www.youtube.com/watch?v=pcdiG6VwqlA

DRGCoder: Explainable Clinical Coding for the Early Prediction of Diagnostic-Related Groups

In the field of Large Language Models (LLMs), researchers are increasingly exploring their effectiveness across a wide range of tasks. 
However, a critical area that requires further investigation is the interpretability of these models, particularly the ability to generate rational explanations for their decisions. Most existing explanation datasets are limited to the English language and the general domain, which leads to a scarcity of linguistic diversity and a lack of resources in specialized domains, such as medical. To mitigate this, we propose ExplainCPE, a challenging medical dataset consisting of over 7K problems from Chinese Pharmacist Examination, specifically tailored to assess the model-generated explanations. From the overall results, only GPT-4 passes the pharmacist examination with a 75.7\% accuracy, while other models like ChatGPT fail. Further detailed analysis of LLM-generated explanations reveals the limitations of LLMs in understanding medical text and executing computational reasoning. With the increasing importance of AI safety and trustworthiness, ExplainCPE takes a step towards improving and evaluating the interpretability of LLMs in the medical domain.

ExplainCPE: A Free-text Explanation Benchmark of Chinese Pharmacist Examination

In this paper, we introduce CAMRA (Copilot for AMR Annotatations), a cutting-edge web-based tool designed for constructing Abstract Meaning Representation (AMR) from natural language text. CAMRA offers a novel approach to deep lexical semantics annotation such as AMR, treating AMR annotation akin to coding in programming languages. Leveraging the familiarity of programming paradigms, CAMRA encompasses all essential features of existing AMR editors, including example lookup, while going a step further by integrating Propbank roleset lookup as an autocomplete feature within the tool. Notably, CAMRA incorporates AMR parser models as coding co-pilots, greatly enhancing the efficiency and accuracy of AMR annotators.

CAMRA: Copilot for AMR Annotation | VIDEO

Large language models have become a vital component in modern NLP, achieving state of the art performance in a variety of tasks.
However, they are often inefficient for real-world deployment due to their expensive inference costs.
Knowledge distillation is a promising technique to improve their efficiency while retaining most of their effectiveness.
In this paper, we reproduce, compare and analyze several representative methods for task-agnostic (general-purpose) distillation of Transformer language models.
Our target of study includes Output Distribution (OD) transfer, Hidden State (HS) transfer with various layer mapping strategies, and Multi-Head Attention (MHA) transfer based on MiniLMv2.
Through our extensive experiments, we study the effectiveness of each method for various student architectures in both monolingual (English) and multilingual settings.
Overall, we show that MHA transfer based on MiniLMv2 is generally the best option for distillation and explain the potential reasons behind its success.
Moreover, we show that HS transfer remains as a competitive baseline, especially under a sophisticated layer mapping strategy, while OD transfer consistently lags behind other approaches.
Findings from this study helped us deploy efficient yet effective student models for latency-critical applications.

A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models | VIDEO

Service accounts, including organizations' official accounts and mini-programs, provide various convenient services for users, and have become crucial components of a number of applications.
Therefore, retrieving service accounts quickly and accurately is vital. However, this task suffers from the problem of limited human annotation, i.e., manually assessing account functionality and assigning ratings based on user experience is both labor-intensive and time-consuming. To this end, this paper proposes a novel approach, the Auxiliary task Boosted Multi-Task Learning method (AuxBoost-MTL). Specifically, the proposed method introduces multiple auxiliary tasks, which is able to utilized the log data from our application as supervision, and enhance the performance of the main task, service account retrieval. Furthermore, we introduce an Adaptive Hierarchical Fusion Module (AHF module) into our approach. This module is designed to adaptively perform hierarchical fusion of embeddings from auxiliary tasks into the main task, thereby enhancing the model efficacy. Experiments on two real-world industrial datasets demonstrate the effectiveness of our proposed approach.

An Auxiliary Task Boosted Multi-task Learning Method for Service Account Retrieval with Limited Human Annotation | VIDEO

Text-video based multimodal event extraction refers to identifying event information from the given text-video pairs. Existing methods predominantly utilize video appearance features (VAF) and text sequence features (TSF) as input information. Some of them employ contrastive learning to align VAF with the event types extracted from TSF. However, they disregard the motion representations in videos and the optimization of contrastive objective could be misguided by the background noise from RGB frames. We observe that the same event triggers correspond to similar motion trajectories, which are hardly affected by the background noise. Moviated by this, we propose a Three Stream Multimodal Event Extraction framework (TSEE) that simultaneously utilizes the features of text sequence and video appearance, as well as the motion representations to enhance the event extraction capacity. Firstly, we extract the optical flow features (OFF) as motion representations from videos to incorporate with VAF and TSF. Then we introduce a Multi-level Event Contrastive Learning module to align the embedding space between OFF and event triggers, as well as between event triggers and types. Finally, a Dual Querying Text module is proposed to enhance the interaction between modalities. Experimental results show that TSEE outperforms the state-of-the-art methods, which demonstrates its superiority.

Three Stream Based Multi-level Event Contrastive Learning for Text-Video Event Extraction

We introduce an encoding for parsing as sequence labeling that can represent any projective dependency tree as a sequence of 4-bit labels, one per word. The bits in each word's label represent (1) whether it is a right or left dependent, (2) whether it is the outermost (left/right) dependent of its parent, (3) whether it has any left children and (4) whether it has any right children. We show that this provides an injective mapping from trees to labels that can be encoded and decoded in linear time. We then define a 7-bit extension that represents an extra plane of arcs, extending the coverage to almost full non-projectivity (over 99.9% empirical arc coverage). Results on a set of diverse treebanks show that our 7-bit encoding obtains substantial accuracy gains over the previously best-performing sequence labeling encodings.

4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees

In the age of neural natural language processing, there are plenty of works trying to derive interpretations of neural models. 
Intuitively, when gold rationales exist during training, one can additionally train the model to match its interpretation with the rationales.
However, this intuitive idea has not been fully explored. In this paper, we propose a framework of utilizing interpretation methods and gold rationales to enhance models. Our framework is very general in the sense that it can incorporate various interpretation methods. Previously proposed gradient-based methods can be shown as an instance of our framework. We also propose two novel instances utilizing two other types of interpretation methods, erasure/replace-based and extractor-based methods, for model enhancement. We conduct comprehensive experiments on a variety of tasks. Experimental results show that our framework is effective especially in low-resource settings in enhancing models with various interpretation methods, and our two newly-proposed methods outperform gradient-based methods in most settings. Code is available at https://github.com/Chord-Chen-30/UIMER.

Using Interpretation Methods for Model Enhancement | VIDEO

The impressive success of recent deep neural network (DNN)-based systems is significantly influenced by the high-quality datasets used in training. However, the effects of the datasets, especially how they interact with each other, remain underexplored. We propose a state-vector framework to enable rigorous studies in this direction. This framework uses idealized probing test results as the bases of a vector space. This framework allows us to quantify the effects of both standalone and interacting datasets. We show that the significant effects of some commonly-used language understanding datasets are characteristic and are concentrated on a few linguistic dimensions. Additionally, we observe some ``spill-over'' effects: the datasets could impact the models along dimensions that may seem unrelated to the intended tasks. Our state-vector framework paves the way for a systematic understanding of the dataset effects, a crucial component in responsible and robust model development.

Underline digital video library

Natural Language Learning via Interaction

Conversation Understanding using Relational Temporal Graph Neural Networks with Auxiliary Cross-Modality Interaction | VIDEO

Unsupervised Sounding Pixel Learning

DRGCoder: Explainable Clinical Coding for the Early Prediction of Diagnostic-Related Groups

ExplainCPE: A Free-text Explanation Benchmark of Chinese Pharmacist Examination

CAMRA: Copilot for AMR Annotation | VIDEO

A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models | VIDEO

An Auxiliary Task Boosted Multi-task Learning Method for Service Account Retrieval with Limited Human Annotation | VIDEO

Three Stream Based Multi-level Event Contrastive Learning for Text-Video Event Extraction

4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees

Using Interpretation Methods for Model Enhancement | VIDEO

A State-Vector Framework for Dataset Effects

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES