Korea, Republic of

Probing studies have extensively explored where in neural language models linguistic information is located. The standard approach to interpreting the results of a probing classifier is to focus on the layers whose representations give the highest performance on the probing task. 
We propose an alternative method that asks where the task-relevant information emerges in the model. Our framework consists of a family of metrics that explicitly model local information gain relative to the previous layer and each layer&#39;s contribution to the model&#39;s overall performance. 
We apply the new metrics to two pairs of syntactic probing tasks with different degrees of complexity and find that the metrics confirm the expected ordering only for one of the pairs. Our local metrics show a massive dominance of the first layers, indicating that the features that contribute the most to our probing tasks are not as high-level as global metrics suggest.

COLING 2022

Where Does Linguistic Information Emerge in Neural Language Models? Measuring Gains and Contributions Across Layers

explainability

probe

probing

interpretability

bertology

[![](https://assets.underline.io/uploads/markdown_image/1/image/81a3c0317d24f663b49b996875024d45.png)](https://aclanthology.org/volumes/2022.coling-1/)



### THE CONFERENCE WE KNOW AND WE WANT.
**COLING**, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes but also in industrial research departments including tech-startups. COLING provides opportunities for all these communities to showcase their exciting discovery.

In fall of 2022, COLING will be held in Gyeongju in a hybrid format. All participants can either present at the venue site or join virtually. As more people get vaccinated, we are happy to provide safer environments for our colleagues. We believe that COLING 2022 will be one of the conferences, free from the pandemic. The hybrid format gives presenters and sponsors a valuable opportunity to promote their companies in both an online and in-person venue. For the first time in a long time, customers can interact with their sponsor's products first-hand. The online venue, too, gives sponsors the chance to network with those unable to attend the in-person session.

The hybrid format ultimately lends itself to greater exposure for our sponsors: COLING2022 will let you reach more potential partners and customers than ever before!<br><br><br>

To gain access to this event page you are required to register.<br> Find more information and pay the registration fee on event the organizer’s website **[https://coling2022.org/reg](https://coling2022.org/reg)**

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

Probing studies have extensively explored where in neural language models linguistic information is located. The standard approach to interpreting the results of a probing classifier is to focus on the layers whose representations give the highest performance on the probing task. 
We propose an alternative method that asks where the task-relevant information emerges in the model. Our framework consists of a family of metrics that explicitly model local information gain relative to the previous layer and each layer's contribution to the model's overall performance. 
We apply the new metrics to two pairs of syntactic probing tasks with different degrees of complexity and find that the metrics confirm the expected ordering only for one of the pairs. Our local metrics show a massive dominance of the first layers, indicating that the features that contribute the most to our probing tasks are not as high-level as global metrics suggest.

poster

Pre-trained language models have made great progress on dialogue tasks. However, these models are typically trained on surface dialogue text, thus are proven to be weak in understanding the main semantic meaning of a dialogue context. We investigate Abstract Meaning Representation (AMR) as explicit semantic knowledge for pre-training models to capture the core semantic information in dialogues during pre-training. In particular, we propose a semantic-based pre-training framework that extends the standard pre-training framework (Devlin et al., 2019) by three tasks for learning 1) core semantic units, 2) semantic relations and 3) the overall semantic representation according to AMR graphs. Experiments on the understanding of both chit-chats and task-oriented dialogues show the superiority of our model. To our knowledge, we are the first to leverage a deep semantic representation for dialogue pre-training.

Semantic-based Pre-training for Dialogue Understanding

Real human conversation data are complicated, heterogeneous, and noisy, from which building open-domain dialogue systems remains a challenging task. In fact, such dialogue data still contains a wealth of information and knowledge, however, they are not fully explored. 
In this paper, we show existing open-domain dialogue generation methods that memorize context-response paired data with autoregressive or encode-decode language models underutilize the training data. Different from current approaches, using external knowledge, we explore a retrieval-generation training framework that can take advantage of the heterogeneous and noisy training data by considering them as "evidence". 
Experiments over publicly available datasets demonstrate that our method can help models generate better responses, even such training data are usually impressed as low-quality data. Such performance gain is comparable with those improved by enlarging the training set, even better. We also found that the model performance has a positive correlation with the relevance of the retrieved evidence. Moreover, our method performed well on zero-shot experiments, which indicates that our method can be more robust to real-world data.

Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation

In this presentation, we will show a more challenging yet practical problem as Continual Few-shot Intent Detection (CFID), where the system needs to handle continually emerging new intents with very few labeled data. To deal with the problem, we propose a novel prefix-guided lightweight encoder with three auxiliary strategies. Extensive experiments demonstrate the effectiveness and efficiency of our method in preventing catastrophic forgetting and encouraging positive knowledge transfer across tasks.

Continual Few-shot Intent Detection

Most existing slot filling models tend to memorize inherent patterns of entities and corresponding contexts from training data. However, these models can lead to system failure or undesirable outputs when being exposed to spoken language perturbation or variation in practice. We propose a perturbed semantic structure awareness transferring method for training perturbation-robust slot filling models. Specifically, we introduce two MLM-based training strategies to respectively learn contextual semantic structure and word distribution from unsupervised language perturbation corpus. Then, we transfer semantic knowledge learned from upstream training procedure into the original samples and filter generated data by consistency processing. These procedures aim to enhance the robustness of slot filling models. Experimental results show that our method consistently outperforms the previous basic methods and gains strong generalization while preventing the model from memorizing inherent patterns of entities and contexts.

PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling

Contextual embeddings build multidimensional representations of word tokens based on their context of occurrence. Such models have been shown to achieve a state-of-the-art performance on a wide variety of tasks. Yet, the community struggles in understanding what kind of semantic knowledge these representations encode. We report a series of experiments aimed at investigating to what extent one of such models, BERT, is able to infer the semantic relations that, according to Dowty’s Proto-Roles theory, a verbal argument receives by virtue of its role
in the event described by the verb. This hypothesis were put to test by learning
a linear mapping from the BERT’s verb embeddings to an interpretable space of semantic properties built from the linguistic dataset by White et al. (2016). In a first experiment we tested whether the semantic properties inferred from a typed version of the BERT embeddings would be more linguistically plausible than those produced by relying on static embeddings. We then move to evaluate the semantic properties inferred from the contextual embeddings both against those available in the original dataset, as well as by assessing their ability to model the semantic properties possessed by the agent of the verbs participating in the so-called causative alternation.

Does BERT recognize an Agent? Modeling Dowty's Proto-Roles with contextual embeddings

Few-shot named entity recognition (NER) aims at identifying named entities based on only few labeled instances. Current few-shot NER methods focus on leveraging existing datasets in the rich-resource domains which might fail in a training-from-scratch setting where no source-domain data is used. To tackle training-from-scratch setting, it is crucial to make full use of the annotation information (the boundaries and entity types). Therefore, in this paper, we propose a novel multi-task (Seed, Expand and Entail) learning framework, SEE-Few, for Few-shot NER without using source domain data. The seeding and expanding modules are responsible for providing as accurate candidate spans as possible for the entailing module. The entailing module reformulates span classification as a textual entailment task, leveraging both the contextual clues and entity type information. All the three modules share the same text encoder and are jointly learned. Experimental results on four benchmark datasets under the training-from-scratch setting show that the proposed method outperformed state-of-the-art few-shot NER methods with a large margin.

SEE-Few: Seed, Expand and Entail for Few-shot Named Entity Recognition

Abstract Meaning Representation (AMR) offers a unified semantic representation for natural language sentences. Thus transformation between AMR and text yields two transition tasks in opposite directions, i.e., Text-to-AMR parsing and AMR-to-Text generation. Existing AMR studies only focus on one-side improvements despite the duality of the two tasks, and their improvements are greatly attributed to the inclusion of large extra training data or complex structure modifications which harm the inference speed. Instead, we propose data-efficient Bidirectional Bayesian learning (BiBL) to facilitate bidirectional information transition by adopting a single-stage multitasking strategy so that the resulting model may enjoy much lighter training at the same time. Evaluation on benchmark datasets shows that our proposed BiBL outperforms strong previous seq2seq refinements without the help of extra data which is indispensable in existing counterpart models.

BiBL: AMR Parsing and Generation with Bidirectional Bayesian Learning

Protecting NLP models against misspellings whether accidental or adversarial has been the object of research interest for the past few years. Existing remediations have typically either compromised accuracy or required full model re-training with each new class of attacks. We propose a novel method of retroactively adding resilience to misspellings to transformer-based NLP models. This robustness
can be achieved without the need for re-training of the original NLP model and with only a minimal loss
of language understanding performance on inputs without misspellings. Additionally we propose a new efficient approximate method of generating adversarial misspellings, which considerably reduces the cost needed to evaluate a model's resilience to adversarial attacks.

MockingBERT: A Method for Retroactively Adding Resilience to NLP Models

Word embeddings are critical for numerous NLP tasks but their evaluation in actual under-resourced settings needs further examination. This paper presents a case study in Bribri, a Chibchan language from Costa Rica. Four experiments were adapted from English: Word similarities, WordSim353 correlations, odd-one-out tasks and analogies. Here we discuss their adaptation to an under-resourced Indigenous language and we use them to measure semantic and morphological learning. We trained 96 word2vec models with different hyperparameter combinations. The best models for this under-resourced scenario were Skip-grams with an intermediate size (100 dimensions) and large window sizes (10). These had an average correlation of r=0.28 with WordSim353, a 76% accuracy in semantic odd-one-out and 70% accuracy in structural/morphological odd-one-out. The performance was lower for the analogies: The best models could find the appropriate semantic target amongst the first 25 results approximately 60% of the times, but could only find the morphological/structural target 11% of the times. Future research needs to further explore the patterns of morphological/structural learning, to examine the behavior of deep learning embeddings, and to establish a human baseline. This project seeks to improve Bribri NLP and ultimately help in its maintenance and revitalization.

Evaluating Word Embeddings in Extremely Under-Resourced Languages: A Case Study in Bribri

A common recent approach to semantic parsing augments sequence-to-sequence models by retrieving and appending a set of training samples, called exemplars. The effectiveness of this recipe is limited by the ability to retrieve informative exemplars that help produce the correct parse, which is especially challenging in low-resource settings. Existing retrieval is commonly based on similarity of query and exemplar inputs. We propose GandR, a retrieval procedure that retrieves exemplars for which outputs are also similar. GandR first generates a preliminary prediction with input-based retrieval. Then, it retrieves exemplars with outputs similar to the preliminary prediction which are used to generate a final prediction. GandR sets the state of the art on multiple low-resource semantic parsing tasks.

Premium content

Where Does Linguistic Information Emerge in Neural Language Models? Measuring Gains and Contributions Across Layers

Downloads

Next from COLING 2022

Semantic-based Pre-training for Dialogue Understanding

Similar lecture

Locally Distributed Activation Vectors for Guided Feature Attribution

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES