arXiv subjects

Thomas Demeester

Publications and source records attributed to Thomas Demeester.

87 records · Page 5Linked to original sources

arXiv2018

Predefined Sparseness in Recurrent Sequence Models

Inducing sparseness while training neural networks has been shown to yield models with a lower memory footprint but similar effectiveness to dense models. However, sparseness is typically induced starting from a dense model, and thus this advantage does not hold during training. We propose techniques to enforce sparseness upfront in recurrent sequence models for NLP applications, to also benefit training. First, in language modeling, we show how to increase hidden state sizes in recurrent layers without increasing the number of parameters, leading to more expressive models. Second, for sequence labeling, we show that word embeddings with predefined sparseness lead to similar performance as dense embeddings, at a fraction of the number of trainable parameters.

cs.LG↗

arXiv2018

Prior Attention for Style-aware Sequence-to-Sequence Models

We extend sequence-to-sequence models with the possibility to control the characteristics or style of the generated output, via attention that is generated a priori (before decoding) from a latent code vector. After training an initial attention-based sequence-to-sequence model, we use a variational auto-encoder conditioned on representations of input sequences and a latent code vector space to generate attention matrices. By sampling the code vector from specific regions of this latent space during decoding and imposing prior attention generated from it in the seq2seq model, output can be steered towards having certain attributes. This is demonstrated for the task of sentence simplification, where the latent code vector allows control over output length and lexical simplification, and enables fine-tuning to optimize for different evaluation metrics.

cs.CL↗

arXiv2018

Jack the Reader - A Machine Reading Framework

Many Machine Reading and Natural Language Understanding tasks require reading supporting text in order to answer questions. For example, in Question Answering, the supporting text can be newswire or Wikipedia articles; in Natural Language Inference, premises can be seen as the supporting text and hypotheses as questions. Providing a set of useful primitives operating in a single framework of related tasks would allow for expressive modelling, and easier model comparison and replication. To that end, we present Jack the Reader (Jack), a framework for Machine Reading that allows for quick model prototyping by component reuse, evaluation of new models on existing datasets as well as integrating new datasets and applying them on a growing set of implemented baseline models. Jack is currently supporting (but not limited to) three tasks: Question Answering, Natural Language Inference, and Link Prediction. It is developed with the aim of increasing research efficiency and code reuse.

cs.CL↗

arXiv2018

An attentive neural architecture for joint segmentation and parsing and its application to real estate ads

In processing human produced text using natural language processing (NLP) techniques, two fundamental subtasks that arise are (i) segmentation of the plain text into meaningful subunits (e.g., entities), and (ii) dependency parsing, to establish relations between subunits. In this paper, we develop a relatively simple and effective neural joint model that performs both segmentation and dependency parsing together, instead of one after the other as in most state-of-the-art works. We will focus in particular on the real estate ad setting, aiming to convert an ad to a structured description, which we name property tree, comprising the tasks of (1) identifying important entities of a property (e.g., rooms) from classifieds and (2) structuring them into a tree format. In this work, we propose a new joint model that is able to tackle the two tasks simultaneously and construct the property tree by (i) avoiding the error propagation that would arise from the subtasks one after the other in a pipelined fashion, and (ii) exploiting the interactions between the subtasks. For this purpose, we perform an extensive comparative study of the pipeline methods and the new proposed joint model, reporting an improvement of over three percentage points in the overall edge F1 score of the property tree. Also, we propose attention methods, to encourage our model to focus on salient tokens during the construction of the property tree. Thus we experimentally demonstrate the usefulness of attentive neural architectures for the proposed joint model, showcasing a further improvement of two percentage points in edge F1 score for our application.

cs.CL↗

arXiv2018

Character-level Recurrent Neural Networks in Practice: Comparing Training and Sampling Schemes

Recurrent neural networks are nowadays successfully used in an abundance of applications, going from text, speech and image processing to recommender systems. Backpropagation through time is the algorithm that is commonly used to train these networks on specific tasks. Many deep learning frameworks have their own implementation of training and sampling procedures for recurrent neural networks, while there are in fact multiple other possibilities to choose from and other parameters to tune. In existing literature this is very often overlooked or ignored. In this paper we therefore give an overview of possible training and sampling schemes for character-level recurrent neural networks to solve the task of predicting the next token in a given sequence. We test these different schemes on a variety of datasets, neural network architectures and parameter settings, and formulate a number of take-home recommendations. The choice of training and sampling scheme turns out to be subject to a number of trade-offs, such as training stability, sampling time, model performance and implementation effort, but is largely independent of the data. Perhaps the most surprising result is that transferring hidden states for correctly initializing the model on subsequences often leads to unstable training behavior depending on the dataset.

cs.LG↗

arXiv2017

Large-Scale User Modeling with Recurrent Neural Networks for Music Discovery on Multiple Time Scales

The amount of content on online music streaming platforms is immense, and most users only access a tiny fraction of this content. Recommender systems are the application of choice to open up the collection to these users. Collaborative filtering has the disadvantage that it relies on explicit ratings, which are often unavailable, and generally disregards the temporal nature of music consumption. On the other hand, item co-occurrence algorithms, such as the recently introduced word2vec-based recommenders, are typically left without an effective user representation. In this paper, we present a new approach to model users through recurrent neural networks by sequentially processing consumed items, represented by any type of embeddings and other context features. This way we obtain semantically rich user representations, which capture a user's musical taste over time. Our experimental analysis on large-scale user data shows that our model can be used to predict future songs a user will likely listen to, both in the short and long term.

cs.IR↗

arXiv2017

Break it Down for Me: A Study in Automated Lyric Annotation

Comprehending lyrics, as found in songs and poems, can pose a challenge to human and machine readers alike. This motivates the need for systems that can understand the ambiguity and jargon found in such creative texts, and provide commentary to aid readers in reaching the correct interpretation. We introduce the task of automated lyric annotation (ALA). Like text simplification, a goal of ALA is to rephrase the original text in a more easily understandable manner. However, in ALA the system must often include additional information to clarify niche terminology and abstract concepts. To stimulate research on this task, we release a large collection of crowdsourced annotations for song lyrics. We analyze the performance of translation and retrieval models on this task, measuring performance with both automated and human evaluation. We find that each model captures a unique type of information important to the task.

cs.CL↗

arXiv2017

Adversarial Sets for Regularising Neural Link Predictors

In adversarial training, a set of models learn together by pursuing competing goals, usually defined on single data instances. However, in relational learning and other non-i.i.d domains, goals can also be defined over sets of instances. For example, a link predictor for the is-a relation needs to be consistent with the transitivity property: if is-a(x_1, x_2) and is-a(x_2, x_3) hold, is-a(x_1, x_3) needs to hold as well. Here we use such assumptions for deriving an inconsistency loss, measuring the degree to which the model violates the assumptions on an adversarially-generated set of examples. The training objective is defined as a minimax problem, where an adversary finds the most offending adversarial examples by maximising the inconsistency loss, and the model is trained by jointly minimising a supervised loss and the inconsistency loss on the adversarial examples. This yields the first method that can use function-free Horn clauses (as in Datalog) to regularise any neural link predictor, with complexity independent of the domain size. We show that for several link prediction models, the optimisation problem faced by the adversary has efficient closed-form solutions. Experiments on link prediction benchmarks indicate that given suitable prior knowledge, our method can significantly improve neural link predictors on all relevant metrics.

cs.AI↗

arXiv2016

Lifted Rule Injection for Relation Embeddings

Methods based on representation learning currently hold the state-of-the-art in many natural language processing and knowledge base inference tasks. Yet, a major challenge is how to efficiently incorporate commonsense knowledge into such models. A recent approach regularizes relation and entity representations by propositionalization of first-order logic rules. However, propositionalization does not scale beyond domains with only few entities and rules. In this paper we present a highly efficient method for incorporating implication rules into distributed representations for automated knowledge base construction. We map entity-tuple embeddings into an approximately Boolean space and encourage a partial ordering over relation embeddings based on implication rules mined from WordNet. Surprisingly, we find that the strong restriction of the entity-tuple embedding space does not hurt the expressiveness of the model and even acts as a regularizer that improves generalization. By incorporating few commonsense rules, we achieve an increase of 2 percentage points mean average precision over a matrix factorization baseline, while observing a negligible increase in runtime.

cs.LG↗

arXiv2016

Resource Selection for Federated Search on the Web

A publicly available dataset for federated search reflecting a real web environment has long been absent, making it difficult for researchers to test the validity of their federated search algorithms for the web setting. We present several experiments and analyses on resource selection on the web using a recently released test collection containing the results from more than a hundred real search engines, ranging from large general web search engines such as Google, Bing and Yahoo to small domain-specific engines. First, we experiment with estimating the size of uncooperative search engines on the web using query based sampling and propose a new method using the ClueWeb09 dataset. We find the size estimates to be highly effective in resource selection. Second, we show that an optimized federated search system based on smaller web search engines can be an alternative to a system using large web search engines. Third, we provide an empirical comparison of several popular resource selection methods and find that these methods are not readily suitable for resource selection on the web. Challenges include the sparse resource descriptions and extremely skewed sizes of collections.

cs.IR↗

arXiv2016

Representation learning for very short texts using weighted word embedding aggregation

Short text messages such as tweets are very noisy and sparse in their use of vocabulary. Traditional textual representations, such as tf-idf, have difficulty grasping the semantic meaning of such texts, which is important in applications such as event detection, opinion mining, news recommendation, etc. We constructed a method based on semantic word embeddings and frequency information to arrive at low-dimensional representations for short texts designed to capture semantic similarity. For this purpose we designed a weight-based model and a learning procedure based on a novel median-based loss function. This paper discusses the details of our model and the optimization methods, together with the experimental results on both Wikipedia and Twitter data. We find that our method outperforms the baseline approaches in the experiments, and that it generalizes well on different word embeddings without retraining. Our method is therefore capable of retaining most of the semantic information in the text, and is applicable out-of-the-box.

cs.IR↗

arXiv2016

Efficiency Evaluation of Character-level RNN Training Schedules

We present four training and prediction schedules from the same character-level recurrent neural network. The efficiency of these schedules is tested in terms of model effectiveness as a function of training time and amount of training data seen. We show that the choice of training and prediction schedule potentially has a considerable impact on the prediction effectiveness for a given training budget.

cs.NE↗

arXiv2016

Knowledge Base Population using Semantic Label Propagation

A crucial aspect of a knowledge base population system that extracts new facts from text corpora, is the generation of training data for its relation extractors. In this paper, we present a method that maximizes the effectiveness of newly trained relation extractors at a minimal annotation cost. Manual labeling can be significantly reduced by Distant Supervision, which is a method to construct training data automatically by aligning a large text corpus with an existing knowledge base of known facts. For example, all sentences mentioning both 'Barack Obama' and 'US' may serve as positive training instances for the relation born_in(subject,object). However, distant supervision typically results in a highly noisy training set: many training sentences do not really express the intended relation. We propose to combine distant supervision with minimal manual supervision in a technique called feature labeling, to eliminate noise from the large and noisy initial training set, resulting in a significant increase of precision. We further improve on this approach by introducing the Semantic Label Propagation method, which uses the similarity between low-dimensional representations of candidate training instances, to extend the training set in order to increase recall while maintaining high precision. Our proposed strategy for generating training data is studied and evaluated on an established test collection designed for knowledge base population tasks. The experimental results show that the Semantic Label Propagation strategy leads to substantial performance gains when compared to existing approaches, while requiring an almost negligible manual annotation effort.

cs.CL↗

arXiv2015

Learning Semantic Similarity for Very Short Texts

Levering data on social media, such as Twitter and Facebook, requires information retrieval algorithms to become able to relate very short text fragments to each other. Traditional text similarity methods such as tf-idf cosine-similarity, based on word overlap, mostly fail to produce good results in this case, since word overlap is little or non-existent. Recently, distributed word representations, or word embeddings, have been shown to successfully allow words to match on the semantic level. In order to pair short text fragments - as a concatenation of separate words - an adequate distributed sentence representation is needed, in existing literature often obtained by naively combining the individual word representations. We therefore investigated several text representations as a combination of word embeddings in the context of semantic pair matching. This paper investigates the effectiveness of several such naive techniques, as well as traditional tf-idf similarity, for fragments of different lengths. Our main contribution is a first step towards a hybrid method that combines the strength of dense distributed representations - as opposed to sparse term matching - with the strength of tf-idf based methods to automatically reduce the impact of less informative terms. Our new approach outperforms the existing techniques in a toy experimental set-up, leading to the conclusion that the combination of word embeddings and tf-idf information might lead to a better model for semantic content within very short text fragments.

cs.IR↗

arXiv2015

Predicting Relevance based on Assessor Disagreement: Analysis and Practical Applications for Search Evaluation

Evaluation of search engines relies on assessments of search results for selected test queries, from which we would ideally like to draw conclusions in terms of relevance of the results for general (e.g., future, unknown) users. In practice however, most evaluation scenarios only allow us to conclusively determine the relevance towards the particular assessor that provided the judgments. A factor that cannot be ignored when extending conclusions made from assessors towards users, is the possible disagreement on relevance, assuming that a single gold truth label does not exist. This paper presents and analyzes the Predicted Relevance Model (PRM), which allows predicting a particular result's relevance for a random user, based on an observed assessment and knowledge on the average disagreement between assessors. With the PRM, existing evaluation metrics designed to measure binary assessor relevance, can be transformed into more robust and effectively graded measures that evaluate relevance towards a random user. It also leads to a principled way of quantifying multiple graded or categorical relevance levels for use as gains in established graded relevance measures, such as normalized discounted cumulative gain (nDCG), which nowadays often use heuristic and data-independent gain values. Given a set of test topics with graded relevance judgments, the PRM allows evaluating systems on different scenarios, such as their capability of retrieving top results, or how well they are able to filter out non-relevant ones. Its use in actual evaluation scenarios is illustrated on several information retrieval test collections.

cs.IR↗