skip to main content


Title: Effective Seed-Guided Topic Discovery by Integrating Multiple Types of Contexts
Instead of mining coherent topics from a given text corpus in a completely unsupervised manner, seed-guided topic discovery methods leverage user-provided seed words to extract distinctive and coherent topics so that the mined topics can better cater to the user’s interest. To model the semantic correlation between words and seeds for discovering topic-indicative terms, existing seedguided approaches utilize different types of context signals, such as document-level word co-occurrences, sliding window-based local contexts, and generic linguistic knowledge brought by pre-trained language models. In this work, we analyze and show empirically that each type of context information has its value and limitation in modeling word semantics under seed guidance, but combining three types of contexts (i.e., word embeddings learned from local contexts, pre-trained language model representations obtained from general-domain training, and topic-indicative sentences retrieved based on seed information) allows them to complement each other for discovering quality topics. We propose an iterative framework, SeedTopicMine, which jointly learns from the three types of contexts and gradually fuses their context signals via an ensemble ranking process. Under various sets of seeds and on multiple datasets, SeedTopicMine consistently yields more coherent and accurate topics than existing seed-guided topic discovery approaches.  more » « less
Award ID(s):
1956151 1741317 1704532
NSF-PAR ID:
10467092
Author(s) / Creator(s):
; ; ; ; ;
Corporate Creator(s):
Editor(s):
Proceedings of the Sixteenth 
Publisher / Repository:
ACM
Date Published:
Edition / Version:
1
Page Range / eLocation ID:
429 to 437
Subject(s) / Keyword(s):
["Seed-Guided Topic Discovery, Integrating Multiple Types of Contexts, Topic mining, text mining"]
Format(s):
Medium: X
Location:
Singapore Singapore
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Recent years have witnessed the enormous success of text representation learning in a wide range of text mining tasks. Earlier word embedding learning approaches represent words as fixed low-dimensional vectors to capture their semantics. The word embeddings so learned are used as the input features of task-specific models. Recently, pre-trained language models (PLMs), which learn universal language representations via pre-training Transformer-based neural models on large-scale text corpora, have revolutionized the natural language processing (NLP) field. Such pre-trained representations encode generic linguistic features that can be transferred to almost any text-related applications. PLMs outperform previous task-specific models in many applications as they only need to be fine-tuned on the target corpus instead of being trained from scratch. In this tutorial, we introduce recent advances in pre-trained text embeddings and language models, as well as their applications to a wide range of text mining tasks. Specifically, we first overview a set of recently developed self-supervised and weakly-supervised text embedding methods and pre-trained language models that serve as the fundamentals for downstream tasks. We then present several new methods based on pre-trained text embeddings and language models for various text mining applications such as topic discovery and text classification. We focus on methods that are weakly-supervised, domain-independent, language-agnostic, effective and scalable for mining and discovering structured knowledge from large-scale text corpora. Finally, we demonstrate with real world datasets how pre-trained text representations help mitigate the human annotation burden and facilitate automatic, accurate and efficient text analyses. 
    more » « less
  2. Existing approaches for learning word embedding often assume there are sufficient occurrences for each word in the corpus, such that the representation of words can be accurately estimated from their contexts. However, in real-world scenarios, out-of-vocabulary (a.k.a. OOV) words that do not appear in training corpus emerge frequently. How to learn accurate representations of these words to augment a pre-trained embedding by only a few observations is a challenging research problem. In this paper, we formulate the learning of OOV embedding as a few-shot regression problem by fitting a representation function to predict an oracle embedding vector (defined as embedding trained with abundant observations) based on limited contexts. Specifically, we propose a novel hierarchical attention network-based embedding framework to serve as the neural regression function, in which the context information of a word is encoded and aggregated from K observations. Furthermore, we propose to use Model-Agnostic Meta-Learning (MAML) for adapting the learned model to the new corpus fast and robustly. Experiments show that the proposed approach significantly outperforms existing methods in constructing an accurate embedding for OOV words and improves downstream tasks when the embedding is utilized. 
    more » « less
  3. Abstract

    During language processing, people make rapid use of contextual information to promote comprehension of upcoming words. When new words are learned implicitly, information contained in the surrounding context can provide constraints on their possible meaning. In the current study, EEG was recorded as participants listened to a series of three sentences, each containing an identical target pseudoword, with the aim of using contextual information in the surrounding language to identify a meaning representation for the novel word. In half of the trials, sentences were semantically coherent so that participants could develop a single representation for the novel word that fit all contexts. Other trials contained unrelated sentence contexts so that meaning associations were not possible. We observed greater theta band enhancement over the left hemisphere across central and posterior electrodes in response to pseudowords processed across semantically related compared to unrelated contexts. Additionally, relative alpha and beta band suppression was increased prior to pseudoword onset in trials where contextual information more readily promoted pseudoword meaning associations. Under the hypothesis that theta enhancement indexes processing demands during lexical access, the current study provides evidence for selective online memory retrieval for novel words learned implicitly in a spoken context.

     
    more » « less
  4. With the advent of pre-trained language models (LMs), increasing research efforts have been focusing on infusing commonsense and domain-specific knowledge to prepare LMs for downstream tasks. These works attempt to leverage knowledge graphs, the de facto standard of symbolic knowledge representation, along with pre-trained LMs. While existing approaches leverage external knowledge, it remains an open question how to jointly incorporate knowledge graphs represented in varying contexts — from local (e.g., sentence), document-level, to global knowledge, to enable knowledge-rich and interpretable exchange across contexts. In addition, incorporating varying contexts can especially benefit long document understanding tasks that leverage pre-trained LMs, typically bounded by the input sequence length. In light of these challenges, we propose KALM, a language model that jointly leverages knowledge in local, document-level, and global contexts for long document understanding. KALM firstly encodes long documents and knowledge graphs into the three knowledge-aware context representations. KALM then processes each context with context-specific layers. These context-specific layers are followed by a ContextFusion layer that facilitates knowledge exchange to derive an overarching document representation. Extensive experiments demonstrate that KALM achieves state-of-the-art performance on three long document understanding tasks across 6 datasets/settings. Further analyses reveal that the three knowledge-aware contexts are complementary and they all contribute to model performance, while the importance and information exchange patterns of different contexts vary on different tasks and datasets. 
    more » « less
  5. Speech processing is highly incremental. It is widely accepted that human listeners continuously use the linguistic context to anticipate upcoming concepts, words, and phonemes. However, previous evidence supports two seemingly contradictory models of how a predictive context is integrated with the bottom-up sensory input: Classic psycholinguistic paradigms suggest a two-stage process, in which acoustic input initially leads to local, context-independent representations, which are then quickly integrated with contextual constraints. This contrasts with the view that the brain constructs a single coherent, unified interpretation of the input, which fully integrates available information across representational hierarchies, and thus uses contextual constraints to modulate even the earliest sensory representations. To distinguish these hypotheses, we tested magnetoencephalography responses to continuous narrative speech for signatures of local and unified predictive models. Results provide evidence that listeners employ both types of models in parallel. Two local context models uniquely predict some part of early neural responses, one based on sublexical phoneme sequences, and one based on the phonemes in the current word alone; at the same time, even early responses to phonemes also reflect a unified model that incorporates sentence-level constraints to predict upcoming phonemes. Neural source localization places the anatomical origins of the different predictive models in nonidentical parts of the superior temporal lobes bilaterally, with the right hemisphere showing a relative preference for more local models. These results suggest that speech processing recruits both local and unified predictive models in parallel, reconciling previous disparate findings. Parallel models might make the perceptual system more robust, facilitate processing of unexpected inputs, and serve a function in language acquisition. MEG Data MEG data is in FIFF format and can be opened with MNE-Python. Data has been directly converted from the acquisition device native format without any preprocessing. Events contained in the data indicate the stimuli in numerical order. Subjects R2650 and R2652 heard stimulus 11b instead of 11. Predictor Variables The original audio files are copyrighted and cannot be shared, but the make_audio folder contains make_clips.py which can be used to extract the exact clips from the commercially available audiobook (ISBN 978-1480555280). The predictors directory contains all the predictors used in the original study as pickled eelbrain objects. They can be loaded in Python with the eelbrain.load.unpickle function. The TextGrids directory contains the TextGrids aligned to the audio files. Source Localization The localization.zip file contains files needed for source localization. Structural brain models used in the published analysis are reconstructed by scaling the FreeSurfer fsaverage brain (distributed with FreeSurfer) based on each subject's `MRI scaling parameters.cfg` file. This can be done using the `mne.scale_mri` function. Each subject's MEG folder contains a `subject-trans.fif` file which contains the coregistration between MEG sensor space and (scaled) MRI space, which is used to compute the forward solution. 
    more » « less