Spain

In this presentation we will explore how we can use probing techniques to gain insight into how multimodal embedding model visual contexts.

Semantic embeddings have advanced the state of the art for countless natural language processing tasks, and various extensions to multimodal domains, such as visual-semantic embeddings, have been proposed. While the power of visual-semantic embeddings comes from the distillation and enrichment of information through machine learning, their inner workings
are poorly understood and there is a shortage of analysis tools. To address this problem, we generalize the notion of probing tasks to the visual-semantic case. To this end, we (i) discuss the formalization of probing tasks for embeddings of image-caption pairs, (ii) define three concrete probing tasks within our general framework, (iii) train classifiers to probe for those properties, and (iv) compare various state-of-the-art embeddings under the lens of the proposed probing tasks. Our experiments reveal an up to 12% increase in accuracy on visual-semantic embeddings compared to the corresponding unimodal embeddings, which suggest that the text and image
dimensions represented in the former do complement each other.

COLING 2020

Probing Multimodal Embeddings for Linguistic Properties: the visual-semantic case

visual-semantic embeddings

multimodal machine learning

probing

interpretability

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

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 and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

technical paper

In the paper, we revisit the PP attachment problem which has been identified as one of the major sources for parser errors and discuss shortcomings of recent work. In particular, we show that using gold information for the extraction of attachment candidates as well as a missing comparison of the system's output to the output of a full syntactic parser leads to an overly optimistic assessment of the results. We address these issues by presenting a realistic evaluation of the potential of different PP attachment systems, using fully predicted information as system input. We compare our results against the output of a strong neural parser and show that the full parsing approach is superior to modeling PP attachment disambiguation as a separate task.

Parsers Know Best: German PP Attachment Revisited

Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model trained on a high-resource language-pair and fine-tuning it on the data of the low-resource MT condition of interest. However, it is not clear generally which high-resource language-pair offers the best transfer learning for the target MT setting. Furthermore, different transferred models may have complementary semantic and/or syntactic strengths, hence using only one model may be sub-optimal. In this paper, we tackle this problem using knowledge distillation, where we propose to distill the knowledge of ensemble of teacher models to a single student model. As the quality of these teacher models varies, we propose an effective adaptive knowledge distillation approach to dynamically adjust the contribution of the teacher models during the distillation process. Experiments on transferring from a collection of six language pairs from IWSLT to five low-resource language-pairs from TED Talks demonstrate the effectiveness of our approach, achieving up to +0.9 BLEU score improvement compared to strong baselines.

Collective Wisdom: Improving Low-resource Neural Machine Translationusing Adaptive Knowledge Distillation

Although neural table-to-text models have achieved remarkable progress with the help of large-scale datasets, they suffer insufficient learning problem with limited training data. Recently, pre-trained language models show potential in few-shot learning with linguistic knowledge learnt from pretraining on large-scale corpus. However, benefiting table-to-text generation in few-shot setting with the powerful pretrained language model faces three challenges, including (1) the gap between the task's structured input and the natural language input for pretraining language model. (2) The lack of modeling for table structure and (3) improving text \textit{fidelity} with less incorrect expressions that are contradicting to the table. To address aforementioned problems, we propose TableGPT for table-to-text generation. At first, we utilize table transformation module with template to rewrite structured table in natural language as input for GPT-2. 
In addition, we exploit multi-task learning with two auxiliary tasks that preserve table's structural information by reconstructing the structure from GPT-2's representation and improving the text's fidelity with content matching task aligning the table and information in the generated text. By experimenting on Humans, Songs and Books, three few-shot table-to-text datasets in different domains, our model outperforms existing systems on most few-shot settings.

TableGPT: Few-shot Table-to-Text Generation with Table Structure Reconstruction and Content Matching

This presentation gives a summary of the paper 'Complaint Identification in Social Media with Transformer Networks', which consists of the introduction of the research topic, predictive models, results and main findings. It focuses on evaluating a battery of transformer-based models applied to complaint identification task and presenting a qualitative analysis which shows the advantages and limitations of transformer models.

Complaint Identification in Social Media with Transformer Networks

Image text carries essential information to understand the scene and perform reasoning. Text-based visual question answering (text VQA) task focuses on visual questions that require reading text in images.
Existing text VQA systems generate an answer by selecting from optical character recognition (OCR) texts or a fixed vocabulary. Positional information of text is underused and there is a lack of evidence for the generated answer. As such, this paper proposes a localization-aware answer prediction network (LaAP-Net) to address this challenge. Our LaAP-Net not only generates the answer to the question but also predicts a bounding box as evidence of the generated answer. Moreover, a context-enriched OCR representation (COR) for multimodal fusion is proposed to facilitate the localization task. Our proposed LaAP-Net outperforms existing approaches on three benchmark datasets for the text VQA task by a noticeable margin.

Finding the Evidence: Localization-aware Answer Prediction for Text Visual Question Answering

A fundamental task of fine-grained sentiment analysis is aspect and opinion terms extraction. Supervised-learning approaches have shown good results for this task; however, they fail to scale across domains where labeled data is lacking. Non pre-trained unsupervised domain adaptation methods that incorporate external linguistic knowledge have proven effective in transferring aspect and opinion knowledge from a labeled source domain to unlabeled target domains; however, pre-trained transformer-based models like BERT and RoBERTa already exhibit substantial syntactic knowledge. 
In this paper, we propose a method for incorporating external linguistic information into a self-attention mechanism coupled with the BERT model. This enables leveraging the intrinsic knowledge existing within BERT together with externally introduced syntactic information, to bridge the gap across domains. Finally, we demonstrate enhanced results on three benchmark datasets.

Syntactically Aware Cross-Domain Aspect and Opinion Terms Extraction

Generating texts which express complex ideas spanning multiple sentences requires a structured representation of their content (document plan), but these representations are prohibitively expensive to manually produce. In this work, we address the problem of generating coherent multi-sentence texts from the output of an information extraction system, and in particular a knowledge graph. Graph- ical knowledge representations are ubiquitous in computing, but pose a significant challenge for text generation techniques due to their non-hierarchical nature, collapsing of long- distance dependencies, and structural variety. We introduce a novel graph transforming en- coder which can leverage the relational structure of such knowledge graphs without imposing linearization or hierarchical constraints. Incorporated into an encoder-decoder setup, we provide an end-to-end trainable system for graph-to-text generation that we apply to the domain of scientific text. Automatic and human evaluations show that our technique produces more informative texts which exhibit better document structure than competitive encoder-decoder methods.

A Graph Representation of Semi-structured Data for Web Question Answering - COLING2020

Span-based joint extraction models have shown their efficiency on entity recognition and relation extraction. These models regard text spans as candidate entities and span tuples as candidate relation tuples. Span semantic representations are shared in both entity recognition and relation extraction, while existing models cannot well capture semantics of these candidate entities and relations. To address these problems, we introduce a span-based joint extraction framework with attention-based semantic representations. Specially, attentions are utilized to calculate semantic representations, including span-specific and contextual ones. We further investigate effects of four attention variants in generating contextual semantic representations. Experiments show that our model outperforms previous systems and achieves state-of-the-art results on ACE2005, CoNLL2004 and ADE.

Span-based Joint Entity and Relation Extraction with Attention-based Span-specific and Contextual Semantic Representations

Modern digital personal assistants interact with users through voice. Therefore, they heavily rely on automatic speech recognition (ASR) in order to convert speech to text and perform further tasks. We introduce EBERT, which stands for EmbraceBERT, with the goal of extracting more robust latent representations for the task of noisy ASR text classification. Conventionally, BERT is fine-tuned for downstream classification tasks using only the [CLS] starter token, with the remaining tokens being discarded. We propose using all encoded transformer tokens and further encode them using a novel attentive embracement layer and multi-head attention layer. This approach uses the otherwise discarded tokens as a source of additional information and the multi-head attention in conjunction with the attentive embracement layer to select important features from clean data during training. This allows for the extraction of a robust latent vector resulting in improved classification performance during testing when presented with noisy inputs. We show the impact of our model on both the Chatbot and Snips corpora for intent classification with ASR error. Results, in terms of F1-score and mean between 10 runs, show that our model significantly outperforms the baseline model. Code, data, and results available at https://github.com/gcunhase/EmbraceBERT.

Attentively Embracing Noise for Robust Latent Representation in BERT

Event extraction plays an important role in legal applications, including case push and auxiliary judgment. However, traditional event structure cannot express the connections between arguments, which are extremely important in legal events. Therefore, this paper defines a dynamic event structure for Chinese legal events. To distinguish between similar events, we design hierarchical event features for event detection. Moreover, to address the problem of long-distance semantic dependence and anaphora resolution in argument classification, we propose a novel pedal attention mechanism to extract the semantic relation between two words through their dependent adjacent words. We label a Chinese legal event dataset and evaluate our model on it. Experimental results demonstrate that our model can surpass other state-of-the-art models.

Probing Multimodal Embeddings for Linguistic Properties: the visual-semantic case

Downloads

Next from COLING 2020

Parsers Know Best: German PP Attachment Revisited

Similar lecture

Classifier Probes May Just Learn from Linear Context Features

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Probing Multimodal Embeddings for Linguistic Properties: the visual-semantic case

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from COLING 2020

Parsers Know Best: German PP Attachment Revisited

Similar lecture

Classifier Probes May Just Learn from Linear Context Features

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads