5

Let's say in an NLP problem, I have a question and some correct answers to that question (say, 10 correct answers).

Is there a way to get a new answer as input, and "calculate" whether it is correct?

Stephen Rauch
  • 1,831
  • 11
  • 23
  • 34
user3712353
  • 161
  • 2

3 Answers3

1

This problem can be solved better if you also include the background text from where the questions have been picked up. Then, firstly train word embeddings on the background text. Further, generate sentence compositionality of the questions as well as their answers using a Recursive Neural Network or some variant. After all these steps you can compute the similarity between compositions of the new answer and given answers to know if it is correct or not.

bkshi
  • 2,303
  • 2
  • 14
  • 23
1

One approach to consider:

You will need a similarity measure (say cosine similarity), S(A,B) between two pieces of text, and a way to threshold this measure.

  • For a specific answer A_i, compute the average of similarity scores S(A_i, A_j) between A_i, and all other answers A_j. Call this Sim_i.
  • Compute Sim_i, for all answers A_i.
  • Take the least of all Sim_i, as the threshold similarity, Sim_T
  • Given a new answer A_new, compute its score, Sim_new with respect to all answers.
  • If Sim_new >= Sim_T, then accept the answer, else reject it.

The idea is that the new answer should be accepted if it is "similar" to other known answers. How similar should it be? This is estimated using the similarity between known answers. This is the broad approach. The similarity measure and threshold computation can be experimented with.

raghu
  • 661
  • 5
  • 4
0

Issue: Whether Qumar's Pandemic Protection Law violates the SPS Agreement and its obligations under the WTO.

  1. Identification of the Applicability of the SPS Agreement: The SPS Agreement applies to measures aimed at protecting human, animal, or plant life or health, and which may affect international trade [SPS Agreement, Article 1]. Qumar's Pandemic Protection Law, which includes a ban on live imports of mink and frozen mink pelts from Agricola, is a measure that directly relates to the protection of animal health and may impact international trade. Therefore, the SPS Agreement applies to the measure complained of.

  2. Analysis of the Relevant Aspects of the Measure in Terms of Applicable Obligations in the SPS Agreement: a. Scientific Justification: Qumar's measure must be based on scientific principles and evidence [SPS Agreement, Article 2]. Agricola could argue that Qumar's ban on mink imports should be supported by scientific evidence demonstrating the risk of SARS-CoV-2 transmission from minks in Agricola to humans or animals in Qumar. If Qumar fails to provide such scientific justification, it may be in violation of its obligations under the SPS Agreement.

b. Necessity and Trade Restrictiveness: According to the SPS Agreement, measures must not be more trade-restrictive than necessary to achieve the appropriate level of protection [SPS Agreement, Article 2.2]. Agricola could argue that Qumar's chosen level of protection may be too high, exceeding that of the OIE guidelines, and thus the ban may not be in conformity with the harmonization provisions of the SPS Agreement ,[object Object], [,[object Object],]. Agricola could challenge the necessity and trade restrictiveness of Qumar's measure based on the lack of scientific evidence supporting the ban.

c. Transparency and Notification: Qumar is obligated to provide transparency and notification of its SPS measures [SPS Agreement, Article 7]. Agricola could verify whether Qumar has fulfilled its obligation by publishing the Pandemic Protection Law and submitting a notification to the WTO Secretariat ,[object Object], [,[object Object],].

  1. Potential Challenge under the TBT Agreement and/or the GATT 1994: Agricola may also consider challenging the measure under the TBT Agreement if it believes that the measure creates unnecessary obstacles to international trade. Additionally, if the measure is found to be inconsistent with the non-discrimination principles of the GATT 1994, Agricola could potentially challenge it under the GATT 1994.

Conclusion: Qumar's Pandemic Protection Law is subject to the SPS Agreement, and Agricola could potentially challenge the measure based on the lack of scientific justification, necessity, trade restrictiveness, and transparency. Additionally, Agricola may consider evaluating the measure for potential challenges under the TBT Agreement and the GATT 1994.