Related papers: Quotation Recommendation and Interpretation Based …
We introduce a novel setting, wherein an agent needs to learn a task from a demonstration of a related task with the difference between the tasks communicated in natural language. The proposed setting allows reusing demonstrations from…
AI agents are being developed to support high stakes decision-making processes from driving cars to prescribing drugs, making it increasingly important for human users to understand their behavior. Policy summarization methods aim to convey…
Recommendation is the task of ranking items (e.g. movies or products) according to individual user needs. Current systems rely on collaborative filtering and content-based techniques, which both require structured training data. We propose…
The search of information in large text repositories has been plagued by the so-called document-query vocabulary gap, i.e. the semantic discordance between the contents in the stored document entities on the one hand and the human query on…
Effective communication requires the ability to refer to specific parts of an observation in relation to others. While emergent communication literature shows success in developing various language properties, no research has shown the…
We present ReFormeR, a pattern-guided approach for query reformulation. Instead of prompting a language model to generate reformulations of a query directly, ReFormeR first elicits short reformulation patterns from pairs of initial queries…
We investigate the behavior of maps learned by machine translation methods. The maps translate words by projecting between word embedding spaces of different languages. We locally approximate these maps using linear maps, and find that they…
Language allows humans to build mental models that interpret what is happening around them resulting in more accurate long-term predictions. We present a novel trajectory prediction model that uses linguistic intermediate representations to…
Deep transformer models have pushed performance on NLP tasks to new limits, suggesting sophisticated treatment of complex linguistic inputs, such as phrases. However, we have limited understanding of how these models handle representation…
In finance, economics and many other fields, observations in a matrix form are often observed over time. For example, many economic indicators are obtained in different countries over time. Various financial characteristics of many…
Large mobility datasets collected from various sources have allowed us to observe, analyze, predict and solve a wide range of important urban challenges. In particular, studies have generated place representations (or embeddings) from…
Current models for quotation attribution in literary novels assume varying levels of available information in their training and test data, which poses a challenge for in-the-wild inference. Here, we approach quotation attribution as a set…
In this work we propose a novel representation learning model which computes semantic representations for tweets accurately. Our model systematically exploits the chronologically adjacent tweets ('context') from users' Twitter timelines for…
Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies. However, it calculates the dependencies between representations without considering the…
Search systems are often focused on providing relevant results for the "now", assuming both corpora and user needs that focus on the present. However, many corpora today reflect significant longitudinal collections ranging from 20 years of…
This paper investigates contextual word representation models from the lens of similarity analysis. Given a collection of trained models, we measure the similarity of their internal representations and attention. Critically, these models…
This communication is based on an original approach linking economical factors to technical and methodological ones. This work is applied to the decision process for mix production. This approach is relevant for costing driving systems. The…
Information Pursuit (IP) is an explainable prediction algorithm that greedily selects a sequence of interpretable queries about the data in order of information gain, updating its posterior at each step based on observed query-answer pairs.…
In modern machine learning, pattern recognition replaces realtime semantic reasoning. The mapping from input to output is learned with fixed semantics by training outcomes deliberately. This is an expensive and static approach which depends…
Distributed representations of words have been shown to capture lexical semantics, as demonstrated by their effectiveness in word similarity and analogical relation tasks. But, these tasks only evaluate lexical semantics indirectly. In this…